© 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. 39956
    Prev
    Next
    INDEX
    Explanations

    actions, conditions, and states

    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
    r
    0.54
    he
    0.54
    I
    0.53
    4
    0.52
    kept
    0.52
    embeddings
    0.50
    D
    0.49
    ard
    0.49
    available
    0.49
    results
    0.49
    POSITIVE LOGITS
     thoracique
    0.46
     Enfer
    0.45
     Engineers
    0.45
     Buffered
    0.44
    价
    0.44
     তপ
    0.44
     보다
    0.44
     अमेर
    0.43
     szín
    0.43
    身份
    0.43
    Activations Density 0.000%

    No Known Activations