© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208158
    Prev
    Next
    INDEX
    Explanations

    string use portion Calendar

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

    compatible specifies access"}, or perhaps more simply, "compatibility and access specifics"

    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
    ствима
    0.45
    ئه
    0.45
    ULES
    0.44
    يله
    0.43
    "};
    0.43
    يتر
    0.42
    시기
    0.42
     particules
    0.41
    ィ
    0.41
    toByteArray
    0.41
    POSITIVE LOGITS
    chic
    0.52
    cient
    0.49
    ac
    0.49
     Brake
    0.49
    es
    0.48
    ago
    0.48
    otonic
    0.48
    weaver
    0.45
    cad
    0.44
    adapter
    0.44
    Activations Density 0.000%

    No Known Activations