© 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. 35658
    Prev
    Next
    INDEX
    Explanations

    Q: or <?xml

    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
     in
    -2.77
    は
    -2.30
     on
    -2.27
    を
    -2.25
    が
    -2.23
     at
    -2.20
    ・・・」
    -2.02
     after
    -1.95
     dikutip
    -1.92
     by
    -1.91
    POSITIVE LOGITS
    為に
    2.34
    様な
    2.33
    ようで
    2.25
    ところに
    2.13
    すっ
    1.95
     travailler
    1.88
    おそ
    1.88
     gorgeous
    1.88
    不由得
    1.88
    ところは
    1.87
    Activations Density 0.000%

    No Known Activations