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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 291
    Prev
    Next
    INDEX
    Explanations

    code return types

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

    public static code constructs

    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
    ineuses
    0.51
    栝
    0.48
     lagoons
    0.47
     eagles
    0.46
    蒺
    0.46
     যাহার
    0.46
     monasteries
    0.46
     engravings
    0.45
     whaling
    0.45
    溽
    0.45
    POSITIVE LOGITS
     void
    1.57
     boolean
    1.48
    void
    1.47
    boolean
    1.47
     int
    1.27
    int
    1.20
     static
    1.18
     String
    1.17
    String
    1.16
     bool
    1.12
    Activations Density 0.003%

    No Known Activations