© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 186357
    Prev
    Next
    INDEX
    Explanations

    Pharo programming language

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

    forth, rebol, apl code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bot
    0.46
     เหล
    0.46
     ตัว
    0.43
     ฮ
    0.42
     Dynamo
    0.42
    ңы
    0.42
     Dani
    0.41
     pot
    0.41
    Bot
    0.40
    LogLevel
    0.40
    POSITIVE LOGITS
    khart
    0.39
    delegate
    0.39
     Delegate
    0.37
    bereit
    0.37
    롱
    0.37
    Rota
    0.36
     روم
    0.36
    스코
    0.36
    好奇
    0.36
     स्का
    0.35
    Activations Density 0.009%

    No Known Activations