© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65509
    Prev
    Next
    INDEX
    Explanations

    multiplexing/demultiplexing, attacks, modulation, tagged, epinephrine, webhooks, button, damage, prizes

    np_acts-logits-general · gemini-2.5-flash-lite

    technical or scientific terms, especially related to biological, mechanical, or electronic systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on long, low‐frequency domain-specific terms—that is, specialized technical or scientific jargon.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    및
    -0.99
    ;
    -0.97
    uló
    -0.83
    atória
    -0.83
    几种
    -0.82
    _
    -0.82
     꽃
    -0.81
       
    -0.81
     
    -0.81
     високо
    -0.80
    POSITIVE LOGITS
     Vereinigte
    1.11
     ferien
    1.02
    ЩИ
    1.02
    toko
    0.98
     padx
    0.97
     alasan
    0.96
     penghar
    0.94
     tungkol
    0.94
     hvorfor
    0.93
    Ό
    0.93
    Activations Density 0.105%

    No Known Activations