© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68906
    Prev
    Next
    INDEX
    Explanations

    to report

    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
     with
    -1.38
     as
    -1.36
    <bos>
    -1.29
     amidst
    -1.26
     two
    -1.22
     in
    -1.19
     despite
    -1.19
    虽说
    -1.16
     allows
    -1.16
    匿名使用者
    -1.15
    POSITIVE LOGITS
    卺
    1.57
    久し
    1.50
    oneof
    1.49
    摃
    1.47
    あー
    1.46
    Should
    1.46
     ſever
    1.46
    probably
    1.45
    蛱
    1.45
    に向けて
    1.43
    Activations Density 0.081%

    No Known Activations