© 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. 2322
    Prev
    Next
    INDEX
    Explanations

    training and learning activities

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

    question endings

    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
     النظر
    0.30
     днев
    0.30
    𝘪
    0.30
     ebenfalls
    0.29
    ப்படுத்தி
    0.29
    த
    0.29
    ir
    0.29
     gigante
    0.29
    زي
    0.29
     සැල
    0.29
    POSITIVE LOGITS
    <0xC2>
    0.64
     例文帳に追加
    0.63
    例文帳に追加
    0.61
    嘅
    0.52
     букмекерлар
    0.50
    🥹
    0.50
     фонбет
    0.49
     😁
    0.49
     🥰
    0.48
     😂
    0.47
    Activations Density 2.385%

    No Known Activations