© 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. 64627
    Prev
    Next
    INDEX
    Explanations

    handling `un` and `allow`

    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
    <bos>
    -2.03
    がありますが
    -1.74
    を
    -1.70
    や
    -1.60
    は
    -1.60
    などを
    -1.52
    Hermoso
    -1.52
    と
    -1.45
    では
    -1.45
    があります
    -1.42
    POSITIVE LOGITS
    為に
    2.11
    ことも
    1.75
    様な
    1.59
    際に
    1.57
    必要がある
    1.56
     klachten
    1.56
    を目指す
    1.55
    方がいい
    1.52
    こともあり
    1.52
    ほら
    1.52
    Activations Density 0.011%

    No Known Activations