© 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. 112988
    Prev
    Next
    INDEX
    Explanations

    ProjectConfigurations

    np_acts-logits-general · gemini-2.5-flash-lite

    code tokens and technical identifiers in programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     that
    -2.31
     if
    -2.05
     on
    -1.70
     for
    -1.67
     other
    -1.59
     when
    -1.47
     our
    -1.44
     those
    -1.36
     If
    -1.36
     Polícia
    -1.34
    POSITIVE LOGITS
    â
    1.54
    !
    1.47
    ：……
    1.41
    の
    1.41
     â
    1.39
     XXVII
    1.28
    olingo
    1.28
    �
    1.27
     què
    1.26
     ("
    1.25
    Activations Density 0.189%

    No Known Activations