© 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. 33475
    Prev
    Next
    INDEX
    Explanations

    code comments and foreign words

    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
     Ganzen
    -1.59
     Heilige
    -1.38
     Werken
    -1.26
     retten
    -1.23
     linken
    -1.23
    𐄁
    -1.21
     he
    -1.19
     rechazo
    -1.17
     максима
    -1.16
     The
    -1.14
    POSITIVE LOGITS
    ↵
    1.66
    τσ
    1.20
     poca
    1.19
     превос
    1.18
     käns
    1.16
     spela
    1.16
    它們
    1.16
    ئت
    1.15
     varmt
    1.15
     adet
    1.14
    Activations Density 0.067%

    No Known Activations