© 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. 34-GEMMASCOPE-RES-131K
    7. 78595
    Prev
    Next
    INDEX
    Explanations

    when how what

    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_34/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
     in
    -1.94
     of
    -1.89
    ;
    -1.76
    ce
    -1.56
    pe
    -1.53
    es
    -1.53
     aumentare
    -1.53
    se
    -1.52
    g
    -1.52
    de
    -1.49
    POSITIVE LOGITS
     and
    5.00
     or
    2.97
    และ
    2.67
     –
    2.03
    หรือ
    1.92
     $-$
    1.89
     및
    1.88
     —
    1.82
     และ
    1.76
    そして
    1.72
    Activations Density 0.475%

    No Known Activations