© 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. 113354
    Prev
    Next
    INDEX
    Explanations

    game developer, editions, variants, `/**`

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

    references to retro computing systems, video games, and technology from the 1980s-1990s, particularly including specific years, model numbers, and technical specifications.

    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
     “
    -1.76
     new
    -1.68
     in
    -1.67
    -1.64
    してない
    -1.64
    だよね
    -1.63
    čenie
    -1.61
    </h2>
    -1.59
    なんだけど
    -1.55
    やった
    -1.52
    POSITIVE LOGITS
     chré
    2.30
    謚
    2.19
     Eſ
    1.98
     vernis
    1.98
     eſt
    1.90
     ſi
    1.88
     uſ
    1.88
     chrétienne
    1.86
     яйцо
    1.83
     laku
    1.82
    Activations Density 0.279%
    No Known Activations