© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10137
    Prev
    Next
    INDEX
    Explanations

    bonus points, snack, track, disc

    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
     an
    -1.92
     what
    -1.71
    渽
    -1.66
     a
    -1.60
     from
    -1.59
    衎
    -1.57
     volna
    -1.55
     peculiarities
    -1.55
     hvordan
    -1.53
    ്ട
    -1.52
    POSITIVE LOGITS
    缡
    1.80
    堪能
    1.77
     usu
    1.70
    िन
    1.67
    up
    1.66
    ších
    1.63
    liziert
    1.62
    歺
    1.62
    es
    1.59
    ！！！”
    1.58
    Activations Density 0.009%

    No Known Activations