© 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. 64266
    Prev
    Next
    INDEX
    Explanations

    otherwise too much

    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
     FORM
    -1.08
    Poder
    -0.96
     ailes
    -0.93
    вобо
    -0.89
    arkt
    -0.88
    FORM
    -0.87
    vų
    -0.85
    aturated
    -0.84
    dolphin
    -0.83
    机的
    -0.82
    POSITIVE LOGITS
     otherwise
    1.28
    Otherwise
    1.11
     Otherwise
    1.09
     слишком
    1.05
     will
    1.04
     too
    1.03
     OTHERWISE
    0.98
     left
    0.92
    otherwise
    0.91
     hacerlo
    0.91
    Activations Density 0.050%

    No Known Activations