© 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. 22874
    Prev
    Next
    INDEX
    Explanations

    bullets, missiles, projectiles

    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
     своей
    -1.52
    they
    -1.51
    :+:
    -1.47
    rophoresis
    -1.45
     flesta
    -1.44
    </sup>
    -1.41
    了一个
    -1.40
    日的
    -1.39
    atization
    -1.39
    __':
    -1.39
    POSITIVE LOGITS
     the
    1.84
     from
    1.76
     to
    1.65
    目光
    1.49
    僕が
    1.45
     Both
    1.43
     into
    1.42
     justamente
    1.42
     kürzlich
    1.41
    nasel
    1.39
    Activations Density 0.038%

    No Known Activations