© 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. 112531
    Prev
    Next
    INDEX
    Explanations

    the the these

    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
     before
    -1.77
     both
    -1.66
     It
    -1.66
     when
    -1.49
    -
    -1.48
    ’
    -1.46
    ,”
    -1.42
    in
    -1.42
     treasurer
    -1.42
     WITH
    -1.41
    POSITIVE LOGITS
     Atlántico
    1.86
     of
    1.60
    onViewCreated
    1.58
    髕
    1.57
    Ԇ
    1.54
     gani
    1.48
    ฿
    1.45
    푣
    1.45
    𓐍
    1.44
    ᨆ
    1.44
    Activations Density 0.027%

    No Known Activations