© 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. 43512
    Prev
    Next
    INDEX
    Explanations

    action, primary classification, propensity, <div>, linear, variable, reporting, husky

    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
    ेंसेस
    0.49
    㦣
    0.48
    焲
    0.46
     каса
    0.46
    ⛸
    0.45
    䡓
    0.44
     गहरी
    0.44
    😰
    0.43
    📼
    0.43
    🖥
    0.43
    POSITIVE LOGITS
     with
    0.52
     through
    0.50
    ვ
    0.50
    with
    0.49
     arms
    0.46
    '
    0.44
    ant
    0.44
     as
    0.44
    path
    0.43
    it
    0.43
    Activations Density 0.014%

    No Known Activations