© 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. 4813
    Prev
    Next
    INDEX
    Explanations

    статистика, годы, объекты

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

    * , . , **

    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
    ڑھ
    1.20
    renderCamera
    1.19
    beatCounter
    1.16
    兩
    1.16
     對
    1.14
    ﮈ
    1.13
    點
    1.12
    ﮑ
    1.09
    ဠ
    1.09
    滿
    1.08
    POSITIVE LOGITS
     по
    2.08
     в
    2.05
     на
    2.05
     при
    2.05
     не
    2.00
     за
    1.98
     про
    1.98
     у
    1.91
     до
    1.89
     с
    1.85
    Activations Density 0.033%

    No Known Activations