© 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. 34-GEMMASCOPE-RES-131K
    7. 78024
    Prev
    Next
    INDEX
    Explanations

    code structure and document headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     happen
    -0.79
     الرغم
    -0.71
     tutta
    -0.69
     podob
    -0.69
    ствие
    -0.69
     Rodney
    -0.68
    ajn
    -0.68
     happened
    -0.67
    做的
    -0.66
     լ
    -0.66
    POSITIVE LOGITS
     collider
    0.77
     Cuenca
    0.77
     衣
    0.76
     Izuku
    0.76
     flea
    0.75
    lastName
    0.74
    ▕
    0.74
     '&
    0.73
    Acute
    0.73
     IOException
    0.73
    Activations Density 0.007%

    No Known Activations