© 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. 100034
    Prev
    Next
    INDEX
    Explanations

    Perl code sections

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

    the separator token "・" (middle dot) in Japanese text or the scope resolution operator "::" in programming code.

    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
    '
    -2.94
    ни
    -1.75
     outpost
    -1.73
    ......
    -1.73
    ----
    -1.72
    Ⲉ
    -1.72
    ‘
    -1.70
    in
    -1.66
    ------
    -1.63
    .......
    -1.63
    POSITIVE LOGITS
    蓠
    2.58
     to
    2.08
    笵
    1.94
    idlertid
    1.90
     ופ
    1.80
     see
    1.77
    翃
    1.76
     Второй
    1.72
     próprias
    1.71
    でしたが
    1.70
    Activations Density 0.001%

    No Known Activations