© 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. 33071
    Prev
    Next
    INDEX
    Explanations

    matched age pregnancies collection therapy

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

    technical or academic terms within specialized disciplines.

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

    The neuron fires on relatively rare, domain‐specific or technical terms (uncommon 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
    OGRAPH
    -0.94
    unduh
    -0.90
     isang
    -0.90
     Demok
    -0.89
     ""))
    -0.89
     Dokter
    -0.89
     Inoc
    -0.88
     panas
    -0.88
     <<=
    -0.87
     utilisateurs
    -0.85
    POSITIVE LOGITS
    velli
    0.94
     세계
    0.92
     сейчас
    0.92
     They
    0.91
     anstatt
    0.90
    There
    0.87
     between
    0.87
     there
    0.87
     at
    0.85
    你和
    0.85
    Activations Density 0.096%

    No Known Activations