Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8971
    Prev
    Next
    INDEX
    Explanations

    Volleyball, anchors, arms resting, interfere, erode

    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
    વાહી
    0.56
     дерев
    0.55
    डेजा
    0.53
     esclusivamente
    0.52
     exclusivement
    0.50
     نزدیک
    0.49
     верши
    0.49
    <unused550>
    0.49
    agamanam
    0.48
     oceanic
    0.48
    POSITIVE LOGITS
     in
    0.55
     tle
    0.51
    ın
    0.49
    rante
    0.49
    4
    0.49
    nov
    0.46
    8
    0.46
    ID
    0.46
    In
    0.46
     e
    0.45
    Activations Density 0.002%

    No Known Activations