© 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. 22-GEMMASCOPE-RES-131K
    7. 64959
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords

    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_22/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
     ALC
    -1.08
     unveils
    -1.08
    generally
    -1.06
    usually
    -0.99
     turner
    -0.96
     dando
    -0.95
     ベルト
    -0.94
    commonly
    -0.93
    learned
    -0.92
    Š
    -0.92
    POSITIVE LOGITS
     when
    1.21
    طع
    1.16
     where
    1.14
     on
    1.10
     will
    1.09
     from
    1.04
     areas
    1.04
     while
    1.03
     decreased
    1.03
     slightly
    1.02
    Activations Density 0.041%

    No Known Activations