© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74313
    Prev
    Next
    INDEX
    Explanations

    released or published

    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_10/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
     Tonnen
    -1.81
     who
    -1.66
     other
    -1.65
    You
    -1.65
    There
    -1.61
    Why
    -1.60
    That
    -1.57
    Like
    -1.55
    It
    -1.52
    Even
    -1.47
    POSITIVE LOGITS
     documentaire
    1.42
    mauer
    1.39
    ista
    1.36
     cerdo
    1.36
    ㅁ
    1.35
    ɸ
    1.34
    uaire
    1.34
    ці
    1.33
     horloge
    1.32
    вот
    1.31
    Activations Density 0.049%

    No Known Activations