© 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. 106685
    Prev
    Next
    INDEX
    Explanations

    capability and possibility

    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
     écout
    -1.00
     käytet
    -0.95
     Regno
    -0.94
     épar
    -0.94
     zorro
    -0.92
    specified
    -0.90
    álja
    -0.86
    Marian
    -0.85
     phénom
    -0.85
    accurate
    -0.84
    POSITIVE LOGITS
     قابل
    2.45
    可
    2.20
     easily
    1.99
     obtainable
    1.95
     can
    1.93
    izable
    1.84
     reachable
    1.84
     recoverable
    1.79
     accessible
    1.78
     able
    1.77
    Activations Density 0.261%

    No Known Activations