© 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. 40-GEMMASCOPE-2-RES-262K
    7. 16287
    Prev
    Next
    INDEX
    Explanations

    foreign or specific lists

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

    statements expressing first-person ability or commitment (modal intent), such as declaring what the speaker can or will do.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     ع
    0.43
     formalism
    0.43
     บุ
    0.43
     antennis
    0.42
     Versuch
    0.42
     выделить
    0.41
     halus
    0.40
     adhes
    0.40
     világ
    0.40
     sumptuous
    0.39
    POSITIVE LOGITS
     દરમ
    0.46
    ؟
    0.41
    ポール
    0.41
     অথবা
    0.41
    Опера
    0.40
    पिछ
    0.39
    LError
    0.39
    뛸
    0.38
    Orientation
    0.38
    ற்கான
    0.38
    Activations Density 0.010%

    No Known Activations