© 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. 16-GEMMASCOPE-2-RES-262K
    4. 13490
    Prev
    Next
    INDEX
    Explanations

    remarkable story, life, process

    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_16_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
    -
    1.00
    rying
    0.78
    ERRY
    0.78
     Williamsburg
    0.77
    romatic
    0.77
     and
    0.76
    ails
    0.75
    IGHT
    0.75
    argar
    0.75
    AND
    0.73
    POSITIVE LOGITS
     in
    1.18
    c
    1.05
    도
    1.04
    在
    0.98
    ات
    0.98
    ও
    0.96
    も
    0.91
     can
    0.91
     في
    0.91
     σε
    0.87
    Activations Density 0.003%

    No Known Activations