© 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. 4400
    Prev
    Next
    INDEX
    Explanations

    applying knowledge or skills

    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
    =");
    0.67
     for
    0.63
    »،
    0.62
    )،
    0.60
    }|\
    0.59
    Пи
    0.59
     a
    0.58
    अन्य
    0.58
    ნობ
    0.58
    ᱷ
    0.57
    POSITIVE LOGITS
    ,
    1.03
    و
    0.73
    ര്‍
    0.67
    с
    0.66
    .
    0.64
    I
    0.63
    u
    0.63
    ทั้งหมด
    0.59
    2
    0.58
    ו
    0.58
    Activations Density 0.003%

    No Known Activations