© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10797
    Prev
    Next
    INDEX
    Explanations

    concerned about harmful consumption

    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
    :
    0.51
     ketika
    0.43
     prosed
    0.43
    濫
    0.42
     Cushing
    0.41
     cropland
    0.41
     Sistemi
    0.41
     quando
    0.40
     When
    0.40
    Bank
    0.40
    POSITIVE LOGITS
     Netherlands
    0.43
    ູ່
    0.42
    友人
    0.42
    その他の
    0.41
     других
    0.41
    镞
    0.41
     родствен
    0.40
     француз
    0.39
    其他
    0.39
     অন্য
    0.38
    Activations Density 0.011%

    No Known Activations