© 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. 85997
    Prev
    Next
    INDEX
    Explanations

    not, no, different

    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
    1.66
    <0x0D>
    1.05
    ну
    0.97
    m
    0.96
    Q
    0.96
    </strong>
    0.95
    ট
    0.92
    મ
    0.91
    ing
    0.90
    อื่นๆ
    0.90
    POSITIVE LOGITS
    ح
    1.30
    ль
    1.24
    ração
    1.20
    ções
    1.13
    ка
    1.09
    ляє
    1.07
    os
    1.05
    em
    1.05
    alya
    1.05
    қу
    1.05
    Activations Density 0.003%

    No Known Activations