© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101118
    Prev
    Next
    INDEX
    Explanations

    tried hard to

    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
     with
    -1.92
     three
    -1.80
     of
    -1.80
     sparked
    -1.77
     focusing
    -1.69
     swiftly
    -1.69
     during
    -1.66
     ostensibly
    -1.65
     spurred
    -1.63
     taking
    -1.63
    POSITIVE LOGITS
    sistent
    1.92
     OTHER
    1.90
    に近い
    1.89
    ;,
    1.80
     pomocou
    1.73
     nonchal
    1.67
     relentless
    1.66
    ,.
    1.63
    ,$
    1.60
    si
    1.59
    Activations Density 0.010%

    No Known Activations