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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67420
    Prev
    Next
    INDEX
    Explanations

    all except

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

    The neuron flags tokens occurring in lines that contain numeric or quantitative data (e.g. percentages, measurements, or other statistics).

    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
    кладки
    -0.94
     ſuch
    -0.94
    WriteLiteral
    -0.91
    ഓ
    -0.87
     poitrine
    -0.84
    ActionCreators
    -0.83
    às
    -0.82
    nologie
    -0.82
     Campe
    -0.81
    EditorBrowsable
    -0.80
    POSITIVE LOGITS
     except
    2.03
    except
    1.68
     but
    1.62
    Except
    1.44
     sauf
    1.41
     excepto
    1.39
     regardless
    1.28
     EXCEPT
    1.19
     Except
    1.16
    regardless
    1.16
    Activations Density 0.081%

    No Known Activations