© 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. 130679
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     múltiples
    -1.22
     our
    -1.20
     or
    -1.19
     komplet
    -1.14
    multiple
    -1.13
     svilupp
    -1.08
     terminó
    -1.05
     çünkü
    -1.05
    Often
    -1.04
    medskip
    -1.03
    POSITIVE LOGITS
     föres
    1.23
    thenia
    1.20
     obedience
    1.18
     HAPPENED
    1.16
    ָה
    1.16
    IVENESS
    1.16
    捻
    1.14
    跺
    1.14
     خواهند
    1.13
    eniem
    1.11
    Activations Density 0.000%

    No Known Activations