© 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. 1371
    Prev
    Next
    INDEX
    Explanations

    towards local

    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
    in
    0.51
     янва
    0.46
    ר
    0.46
    ১৯
    0.44
    into
    0.44
    ال
    0.44
     Frobenius
    0.43
     सारी
    0.43
    କ
    0.43
    癃
    0.42
    POSITIVE LOGITS
    ,
    0.54
    </i>
    0.44
    )!
    0.41
    </s>
    0.40
    )|
    0.40
     를
    0.39
     amenity
    0.38
     putea
    0.37
    ну
    0.37
    ды
    0.37
    Activations Density 0.000%

    No Known Activations