© 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. 34-GEMMASCOPE-RES-131K
    7. 30269
    Prev
    Next
    INDEX
    Explanations

    _interopRequireDefault

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Symmetric
    -0.79
     implanted
    -0.76
    ariamente
    -0.76
    Impact
    -0.75
     carrière
    -0.72
    产生了
    -0.72
    cheibe
    -0.71
    Merck
    -0.71
    ECTOS
    -0.70
    cidas
    -0.70
    POSITIVE LOGITS
    nh
    0.66
    敏
    0.65
    vieja
    0.64
     come
    0.61
     作
    0.61
     mask
    0.61
     maken
    0.60
    midrule
    0.60
    come
    0.60
     dibandingkan
    0.60
    Activations Density 0.050%

    No Known Activations