© 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. 295
    Prev
    Next
    INDEX
    Explanations

    powerful adjective

    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
    manam
    0.75
    u
    0.72
    C
    0.68
    ール
    0.63
    mathbf
    0.63
    infty
    0.63
    ER
    0.62
    ма
    0.62
    o
    0.62
    و
    0.61
    POSITIVE LOGITS
    </b>
    0.60
     engine
    0.55
    ↵
    0.54
    </h3>
    0.54
    0.54
     powerful
    0.53
     puiss
    0.52
     have
    0.52
     potent
    0.52
    0.51
    Activations Density 0.232%

    No Known Activations