© 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. 9605
    Prev
    Next
    INDEX
    Explanations

    common designs and types

    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
     verheir
    -1.34
    quantidade
    -1.33
    suporte
    -1.31
    isait
    -1.30
    €™
    -1.25
    懨
    -1.23
     ativar
    -1.23
    alers
    -1.21
     mensen
    -1.20
    ními
    -1.20
    POSITIVE LOGITS
     palab
    1.37
    ятся
    1.37
    靭
    1.36
     since
    1.34
     boute
    1.33
     pulumi
    1.33
     salomon
    1.30
    靱
    1.28
     of
    1.26
     for
    1.26
    Activations Density 0.413%

    No Known Activations