© 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. 22-GEMMASCOPE-RES-131K
    7. 64258
    Prev
    Next
    INDEX
    Explanations

    clarification or qualifier

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ၀
    -1.01
     out
    -0.89
    usschuss
    -0.89
     Stratford
    -0.82
    izarro
    -0.81
     शुर
    -0.81
     our
    -0.81
    することは
    -0.78
    entlich
    -0.77
    ⛺
    -0.76
    POSITIVE LOGITS
     kembali
    1.04
    IMPORTANT
    1.01
     ключе
    0.98
    emphasis
    0.98
     важно
    0.94
     qualifier
    0.93
     新品
    0.92
     revient
    0.92
    라는
    0.91
     element
    0.91
    Activations Density 0.046%

    No Known Activations