© 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. 40040
    Prev
    Next
    INDEX
    Explanations

    emphasized text

    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
    -2.25
     for
    -2.14
     through
    -1.94
    of
    -1.93
     on
    -1.88
     while
    -1.88
    there
    -1.71
    h
    -1.68
    when
    -1.67
     during
    -1.63
    POSITIVE LOGITS
    傒
    1.80
    ⢅
    1.75
    irmingham
    1.65
    
    1.64
    vige
    1.59
     cerámica
    1.56
    ㄸ
    1.56
    ($__
    1.52
     estatua
    1.52
     anſ
    1.52
    Activations Density 0.002%

    No Known Activations