© 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. 71222
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
     чрезвы
    -1.34
     tendría
    -1.26
    ayant
    -1.24
    大好きです
    -1.24
     επίσης
    -1.23
     considér
    -1.23
    éton
    -1.23
     retraso
    -1.21
     pudieron
    -1.21
    boite
    -1.20
    POSITIVE LOGITS
     this
    1.38
    (\%)
    1.34
     that
    1.32
     as
    1.30
     ڤ
    1.24
     their
    1.19
    ;*/
    1.16
     qx
    1.15
    alties
    1.13
    :.
    1.12
    Activations Density 0.015%

    No Known Activations