© 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. 32885
    Prev
    Next
    INDEX
    Explanations

    up, down, out, or top

    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
    Not in Any Lists

    No Comments

    Negative Logits
    を
    -2.44
    や
    -2.17
    <bos>
    -2.16
    が
    -2.13
    そして
    -1.90
    も
    -1.88
    があり
    -1.85
    と
    -1.85
    は
    -1.84
    つまり
    -1.83
    POSITIVE LOGITS
    為に
    2.64
    corrhi
    2.53
    ところに
    2.27
    来週
    2.23
    えっ
    2.23
    感じで
    2.13
    さぁ
    2.13
    あぁ
    2.09
    際に
    2.09
    ことも
    2.09
    Activations Density 0.040%

    No Known Activations