© 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. 68546
    Prev
    Next
    INDEX
    Explanations

    Objective-C format specifiers

    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
     '
    -2.84
    ︓
    -2.73
     murky
    -2.20
    泺
    -2.16
    ;//
    -2.08
     It
    -2.05
    например
    -2.03
     vehement
    -1.98
     '[
    -1.98
     =
    -1.97
    POSITIVE LOGITS
    ↵
    2.70
    .
    2.58
    the
    2.36
    </sub>
    2.23
     they
    2.05
     لهم
    2.02
    THE
    1.96
    却不
    1.96
    ‘‘
    1.95
    ’’
    1.93
    Activations Density 0.000%

    No Known Activations