© 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. 127716
    Prev
    Next
    INDEX
    Explanations

    I don't get

    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
     and
    -2.08
     it
    -1.64
     which
    -1.63
    ølge
    -1.53
     ARXIV
    -1.52
    bezpiec
    -1.50
    perity
    -1.49
    fiques
    -1.48
    thang
    -1.43
    thinkable
    -1.41
    POSITIVE LOGITS
     desempenho
    1.46
     already
    1.46
    ,”
    1.43
    着一个
    1.41
    单纯
    1.41
     =
    1.37
     território
    1.35
    zzlement
    1.35
     currently
    1.34
     jestli
    1.34
    Activations Density 0.128%

    No Known Activations