© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 182317
    Prev
    Next
    INDEX
    Explanations

    left hand

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

    code and programming 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_31_width_262k_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
    き
    0.53
    c
    0.49
    蕾
    0.46
    モール
    0.46
    padx
    0.45
    үндө
    0.44
    られて
    0.44
    办公
    0.44
    村
    0.43
    懺
    0.43
    POSITIVE LOGITS
    You
    0.46
    If
    0.45
    two
    0.44
    Bit
    0.44
     Bit
    0.43
    Sant
    0.43
    Peri
    0.43
    ~~~~~~~~~~~~~~~~
    0.43
     यदि
    0.42
     चिह्न
    0.42
    Activations Density 0.000%

    No Known Activations