© 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. 1991
    Prev
    Next
    INDEX
    Explanations

    diverse scripts

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

    adaptation, bad responses

    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
    }());
    0.59
     cursory
    0.49
     ไม่
    0.47
     oito
    0.46
     १८
    0.46
    则
    0.45
     Từ
    0.45
    در
    0.44
     ইউনিভার্সিটি
    0.44
     በት
    0.43
    POSITIVE LOGITS
     ახ
    0.61
     おしゃれ
    0.53
    addEventListener
    0.52
    上海
    0.52
    apache
    0.51
     上海
    0.49
    አ
    0.48
    啊
    0.48
     आप
    0.48
    ახ
    0.48
    Activations Density 0.533%

    No Known Activations