© 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. 10-GEMMASCOPE-RES-131K
    7. 84421
    Prev
    Next
    INDEX
    Explanations

    prompt actions and outcomes

    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
     astute
    -2.38
     unbelievably
    -2.36
    он
    -2.28
    ⟞
    -2.25
     of
    -2.22
    哙
    -2.19
     amazingly
    -2.17
    蟥
    -2.14
    ocidade
    -2.14
    actéristi
    -2.08
    POSITIVE LOGITS
    It
    2.89
    If
    2.86
    Even
    2.73
    There
    2.73
    \
    2.63
     fédé
    2.61
    b
    2.61
    Every
    2.55
    Although
    2.52
    Having
    2.48
    Activations Density 0.003%

    No Known Activations