© 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. 16-GEMMASCOPE-2-RES-262K
    7. 141763
    Prev
    Next
    INDEX
    Explanations

    dwarf cleric, IMAX documentary, nude woman

    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
    rte
    0.50
     hadde
    0.49
    linic
    0.48
    Ԁ
    0.48
    veh
    0.47
     ملازمت
    0.47
    inite
    0.47
    equipped
    0.47
    bower
    0.46
    their
    0.46
    POSITIVE LOGITS
    ス
    0.61
    ك
    0.54
    س
    0.53
    <strong>
    0.52
     differentials
    0.51
    大
    0.51
    シ
    0.51
    ж
    0.51
    스럽
    0.50
    々
    0.50
    Activations Density 0.000%

    No Known Activations