© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18033
    Prev
    Next
    INDEX
    Explanations

    requires understanding

    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
    FlaskApp
    0.45
     জন্যই
    0.40
    ಲಾ
    0.40
    কাতে
    0.40
    flatable
    0.39
     ሴ
    0.38
     positron
    0.38
    フォルト
    0.38
    槅
    0.38
    烺
    0.37
    POSITIVE LOGITS
    :
    0.42
     of
    0.40
     to
    0.39
     which
    0.38
     избе
    0.38
    higher
    0.38
     priorities
    0.37
    find
    0.37
    which
    0.37
     Higher
    0.37
    Activations Density 0.000%

    No Known Activations