© 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. 9367
    Prev
    Next
    INDEX
    Explanations

    first stages or initial parts

    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
    taan
    -0.89
    cinogenicity
    -0.85
    зад
    -0.82
     their
    -0.82
    xido
    -0.81
     tampoco
    -0.81
     їх
    -0.80
     Lamar
    -0.80
    ghế
    -0.79
     grounds
    -0.79
    POSITIVE LOGITS
     initial
    1.33
     first
    1.14
    initial
    1.08
    Initial
    1.06
     inicial
    1.02
     první
    1.00
     primeiro
    0.98
     pierws
    0.96
     zuerst
    0.96
     primeras
    0.96
    Activations Density 0.111%

    No Known Activations