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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27202
    Prev
    Next
    INDEX
    Explanations

    religious, political, national identifiers

    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
    ところです
    -1.75
    ところに
    -1.66
    色々と
    -1.39
    凄く
    -1.37
    けっこう
    -1.36
    為に
    -1.34
    を買う
    -1.33
    に似
    -1.33
    ホント
    -1.30
    せっ
    -1.30
    POSITIVE LOGITS
     who
    2.84
     whose
    2.03
     with
    1.60
     during
    1.56
     that
    1.52
     from
    1.47
     in
    1.40
     whom
    1.38
     at
    1.32
     amidst
    1.30
    Activations Density 0.141%

    No Known Activations