© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-16K
    4. 3835
    Prev
    Next
    INDEX
    Explanations

    answer preceded by formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <eos>
    1.93
     阅读全文
    1.83
     […]
    1.79
    ↵↵
    1.59
    <b>
    1.56
    ↵↵↵↵
    1.50
    ↵↵↵
    1.49
    ↵↵↵↵↵
    1.46
     例文帳に追加
    1.45
     继续访问
    1.37
    POSITIVE LOGITS
    </strong>
    3.00
    :**
    2.84
    </h4>
    2.73
    :}
    2.66
    </b>
    2.44
    </h1>
    2.42
    '}
    2.36
    </th>
    2.24
    **:
    2.20
    /}{
    2.19
    Activations Density 2.257%

    No Known Activations