© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 27706
    Prev
    Next
    INDEX
    Explanations

    checking in

    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_65k_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
    <0x0D>
    0.95
    </h2>
    0.78
    </u>
    0.78
    ],
    0.75
    ,}
    0.74
    </th>
    0.72
    ;
    0.72
    </b>
    0.71
    )}.
    0.70
    </h4>
    0.68
    POSITIVE LOGITS
    Check
    0.80
    ü
    0.79
    ด
    0.79
     Check
    0.76
     チェック
    0.75
    ב
    0.75
    ut
    0.73
     on
    0.71
    CHECK
    0.71
     decentral
    0.71
    Activations Density 0.065%

    No Known Activations