© 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. 63450
    Prev
    Next
    INDEX
    Explanations

    partially or qualified states

    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
    &
    -1.21
     étages
    -1.08
     exactement
    -0.98
     naturellement
    -0.98
    だけではなく
    -0.98
     dokładnie
    -0.95
     asemenea
    -0.95
     Metern
    -0.94
     prenn
    -0.94
    tauscht
    -0.93
    POSITIVE LOGITS
     SOME
    2.92
     some
    2.73
     partially
    2.48
     хоть
    2.45
     algunos
    2.42
     immerhin
    2.33
     некоторых
    2.33
     algunas
    2.31
     некоторые
    2.28
    บ้าง
    2.28
    Activations Density 0.174%

    No Known Activations