© 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. 99019
    Prev
    Next
    INDEX
    Explanations

    para followed by common words

    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
    Not in Any Lists

    No Comments

    Negative Logits
    厹
    -2.83
    ⩴
    -2.64
    ?"
    -2.50
    欷
    -2.45
     gebeten
    -2.42
    でした
    -2.41
    puede
    -2.39
    踽
    -2.38
     puedes
    -2.36
    謌
    -2.34
    POSITIVE LOGITS
    0
    2.64
     Several
    2.39
     Some
    2.38
    т
    2.38
     Various
    2.30
    เกง
    2.23
    到達
    2.20
     Before
    2.19
     Reaching
    2.19
     Compared
    2.17
    Activations Density 0.001%

    No Known Activations