© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16910
    Prev
    Next
    INDEX
    Explanations

    just let me know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intranet
    0.40
     resultSet
    0.40
     .;
    0.40
     luncheon
    0.39
     کرنے
    0.39
    !;
    0.38
    IVERY
    0.38
     gratuite
    0.37
     genoemd
    0.37
     expiration
    0.37
    POSITIVE LOGITS
    ешь
    0.47
    oubliez
    0.46
    si
    0.45
    留意
    0.43
    uz
    0.43
    s
    0.43
    鎚
    0.43
    ników
    0.43
    nb
    0.43
    ce
    0.42
    Activations Density 0.030%

    No Known Activations