© 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. 98770
    Prev
    Next
    INDEX
    Explanations

    "Best Buy" and "Best Picture"

    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
    ็จ
    -1.92
    
    -1.90
    ----</
    -1.88
     丁目
    -1.74
     SUCH
    -1.66
    》(
    -1.64
    âncias
    -1.64
    lysm
    -1.63
    !»
    -1.60
    phorbia
    -1.58
    POSITIVE LOGITS
    and
    2.13
    v
    2.06
    IT
    2.00
    on
    1.98
    *
    1.86
    ...
    1.83
    ll
    1.82
    to
    1.82
     a
    1.80
    ?
    1.80
    Activations Density 0.002%

    No Known Activations