© 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. 106692
    Prev
    Next
    INDEX
    Explanations

    establishments and organizations

    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
     people
    -1.23
     being
    -1.19
     arrivato
    -1.13
     its
    -1.13
     for
    -1.11
    řevě
    -1.05
     someone
    -1.02
    Продам
    -0.99
     mengakibatkan
    -0.95
     at
    -0.95
    POSITIVE LOGITS
     that
    1.92
     которые
    1.45
     whose
    1.28
     who
    1.27
     and
    1.23
     που
    1.21
    operating
    1.20
    whose
    1.20
    llllll
    1.20
     które
    1.17
    Activations Density 0.093%

    No Known Activations