© 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. 72806
    Prev
    Next
    INDEX
    Explanations

    cells

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

    suffixes or endings of scientific or technical terms.

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

    The neuron fires on content‐bearing, domain-specific or technical terms (i.e. uncommon, non-function words that carry specialized meaning).

    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
    strip
    -0.93
    afari
    -0.85
    prises
    -0.85
     إلى
    -0.85
    Λ
    -0.84
     لهذه
    -0.82
    ￩
    -0.82
     этих
    -0.81
    𝓇
    -0.81
    renti
    -0.79
    POSITIVE LOGITS
    尔夫
    1.09
     from
    0.96
     starting
    0.93
     likely
    0.88
    場所で
    0.88
     without
    0.83
     become
    0.82
     started
    0.82
     nahmen
    0.82
     stayed
    0.79
    Activations Density 0.094%

    No Known Activations