© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98850
    Prev
    Next
    INDEX
    Explanations

    imaginary circus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </b>
    -2.36
    </td>
    -2.36
     THEIR
    -2.09
    
    -2.06
    痈
    -2.02
    逦
    -2.00
    з
    -1.98
     were
    -1.95
    来て
    -1.92
    窳
    -1.92
    POSITIVE LOGITS
    </strong>
    2.72
    ).
    2.67
    the
    2.61
    y
    2.53
    </h3>
    2.39
    "
    2.39
    !”
    2.36
    d
    2.31
    ul
    2.27
     unequivocal
    2.23
    Activations Density 0.001%

    No Known Activations