© 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. 113791
    Prev
    Next
    INDEX
    Explanations

    video game titles

    np_acts-logits-general · gemini-2.5-flash-lite

    video game titles and franchises, particularly in gaming-related content.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    Один
    -1.53
    Внимание
    -1.51
    Сколько
    -1.50
    Ꮴ
    -1.47
    Итак
    -1.46
    對於
    -1.45
    Новые
    -1.43
    Дере
    -1.43
    ländern
    -1.41
     lunedì
    -1.41
    POSITIVE LOGITS
    —
    1.54
    :
    1.47
    --
    1.45
     all
    1.44
     your
    1.41
     In
    1.37
    ']
    1.35
     any
    1.34
     to
    1.30
     de
    1.30
    Activations Density 0.059%

    No Known Activations