© 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. 57068
    Prev
    Next
    INDEX
    Explanations

    initialisms and abbreviations

    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
    kontrol
    -0.81
     proti
    -0.81
    擀
    -0.77
     CONTROLS
    -0.76
     kontrol
    -0.74
     controls
    -0.74
     concr
    -0.73
    voked
    -0.71
    太平
    -0.71
     Leith
    -0.69
    POSITIVE LOGITS
     otro
    0.85
    鬱
    0.71
     Gefühl
    0.71
    閣
    0.70
     šir
    0.69
    بسم
    0.69
    筹
    0.69
    bronn
    0.68
     praktijk
    0.68
    LookAnd
    0.68
    Activations Density 0.018%

    No Known Activations