© 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. 4139
    Prev
    Next
    INDEX
    Explanations

    view live, changes, newest, page, angle

    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
    s
    1.34
    i
    1.32
    al
    1.20
    that
    1.11
    name
    0.94
    br
    0.93
    belief
    0.93
    ي
    0.92
    te
    0.90
    band
    0.88
    POSITIVE LOGITS
    ст
    1.00
    '
    0.91
    க்க
    0.91
    มี
    0.91
    ка
    0.90
    ナ
    0.89
    จะ
    0.89
    в
    0.88
    の
    0.88
    의
    0.86
    Activations Density 0.016%

    No Known Activations