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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5174
    Prev
    Next
    INDEX
    Explanations

    Croatia and dates

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

    mathematical operations

    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_53_width_65k_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
    萂
    0.44
    螌
    0.42
    ړئ
    0.41
     ditth
    0.41
    帐户
    0.40
     gợi
    0.39
    ार्थ
    0.39
    䒩
    0.39
    ),\\
    0.38
    тету
    0.38
    POSITIVE LOGITS
    thousand
    0.55
     thousand
    0.55
     nineteen
    0.54
     thousands
    0.48
     hundred
    0.48
     Hundred
    0.48
     ninety
    0.47
     labored
    0.47
     Dollars
    0.46
    Hundred
    0.46
    Activations Density 0.022%

    No Known Activations