© 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. 117605
    Prev
    Next
    INDEX
    Explanations

    state change

    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
    敺
    -0.94
     GONE
    -0.93
    はなく
    -0.88
    больше
    -0.87
    groupName
    -0.87
     declining
    -0.85
    Gone
    -0.85
     disappearance
    -0.85
    {\"
    -0.84
    reado
    -0.84
    POSITIVE LOGITS
    falt
    0.79
     tež
    0.78
    jard
    0.77
    theoremstyle
    0.77
     Internasional
    0.76
    もし
    0.76
    Agosto
    0.74
     člove
    0.74
    אלי
    0.73
    パリ
    0.73
    Activations Density 0.071%

    No Known Activations