© 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. 1773
    Prev
    Next
    INDEX
    Explanations

    work, Miche, estate

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

    stolen radishes, forgotten tools

    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
    ="${
    0.41
     मणिपुर
    0.40
    *********/
    0.40
    рактери
    0.39
     cristian
    0.39
    <0x9F>
    0.39
     Stiftung
    0.39
    人人
    0.39
    лика
    0.38
    ="<%=
    0.38
    POSITIVE LOGITS
     texture
    0.45
     wing
    0.45
     bubbles
    0.43
     pancake
    0.42
     rope
    0.41
     butter
    0.41
    blica
    0.41
    zio
    0.41
     ill
    0.40
     wilderness
    0.40
    Activations Density 0.000%

    No Known Activations