© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16378
    Prev
    Next
    INDEX
    Explanations

    medical, legal, or technical queries

    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
     for
    -1.63
     madu
    -1.40
     chré
    -1.37
     hama
    -1.36
     gti
    -1.36
     メニュー
    -1.35
     marta
    -1.35
     muſt
    -1.33
     susu
    -1.30
    хам
    -1.30
    POSITIVE LOGITS
    giày
    1.49
    bbing
    1.41
    PUESTA
    1.39
     rief
    1.39
     indicó
    1.37
    İyi
    1.35
     manifestó
    1.34
     detalló
    1.34
     office
    1.33
     徒歩
    1.33
    Activations Density 0.003%

    No Known Activations