© 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. 36407
    Prev
    Next
    INDEX
    Explanations

    technical terms and materials

    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
    savevideo
    -1.23
     coklat
    -1.18
     куртка
    -1.16
     einsetzen
    -1.13
    Many
    -1.13
     iaitu
    -1.12
     cokelat
    -1.09
     veranstal
    -1.09
    Fuckin
    -1.08
     expresar
    -1.07
    POSITIVE LOGITS
    缡
    1.17
    ⫹
    1.17
     but
    1.10
    lizing
    1.09
     utilisent
    1.07
     süd
    1.07
     También
    1.05
    𝑂
    1.05
    чера
    1.05
     लेकिन
    1.05
    Activations Density 0.179%

    No Known Activations