© 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. 6909
    Prev
    Next
    INDEX
    Explanations

    takeaways from, entertainer who, foray into

    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
    Q
    -2.92
    K
    -2.61
    ↵
    -2.48
    H
    -2.44
    4
    -2.42
    ஂ
    -2.39
    稣
    -2.33
    3
    -2.31
    S
    -2.25
    2
    -2.23
    POSITIVE LOGITS
    ᥬ
    2.59
    琑
    2.48
    uxxxx
    2.39
    ╽
    2.31
    喾
    2.19
    甗
    2.17
    ТОВ
    2.09
    嗐
    2.09
    猁
    2.08
    岀
    2.06
    Activations Density 0.002%

    No Known Activations