© 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. 59661
    Prev
    Next
    INDEX
    Explanations

    alternatives and contrasts

    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
    
    -1.72
    ౮
    -1.62
     maniere
    -1.57
     ondu
    -1.55
    ⧠
    -1.55
     isComment
    -1.55
     elegante
    -1.55
     ſou
    -1.53
     ultime
    -1.53
     bede
    -1.53
    POSITIVE LOGITS
     or
    2.88
     because
    2.23
     people
    2.06
     However
    1.91
     several
    1.84
     many
    1.82
     numerous
    1.81
     although
    1.77
     and
    1.72
     but
    1.70
    Activations Density 0.067%

    No Known Activations