© 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. 36405
    Prev
    Next
    INDEX
    Explanations

    prints, echoes, and calls

    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
     favoris
    -1.45
     plafon
    -1.39
     rése
    -1.27
     poils
    -1.24
     fidé
    -1.21
     blé
    -1.18
    鳚
    -1.11
    ᠁
    -1.11
     parfüm
    -1.11
     prestig
    -1.10
    POSITIVE LOGITS
    A
    1.41
    la
    1.41
    b
    1.38
    R
    1.38
    J
    1.34
    m
    1.34
    M
    1.30
    ul
    1.30
    H
    1.30
    ur
    1.26
    Activations Density 0.014%

    No Known Activations