© 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. 83737
    Prev
    Next
    INDEX
    Explanations

    first or ordinal numbers

    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
    s
    -4.38
    Y
    -3.31
    \
    -2.89
    ]
    -2.78
    *
    -2.64
    O
    -2.47
    E
    -2.45
    ‌هایی
    -2.41
    said
    -2.41
    H
    -2.38
    POSITIVE LOGITS
     continúas
    3.77
    ݮ
    2.92
    ⡪
    2.84
    もあった
    2.77
    
    2.72
    躄
    2.66
     hablaba
    2.64
     utilice
    2.64
     dibujado
    2.63
    蜮
    2.61
    Activations Density 0.003%

    No Known Activations