© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75065
    Prev
    Next
    INDEX
    Explanations

    numbers and 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
    ar
    -1.28
     alcune
    -1.20
    jublj
    -1.17
    了她
    -1.15
     freakin
    -1.13
     gigantic
    -1.09
    見ると
    -1.09
     realizar
    -1.09
     En
    -1.07
     determinados
    -1.07
    POSITIVE LOGITS
    adakan
    1.68
     comerci
    1.57
    oys
    1.57
     leher
    1.38
     Sjö
    1.32
     februar
    1.32
     transparan
    1.32
    tadores
    1.31
     bombas
    1.31
     minas
    1.30
    Activations Density 0.002%

    No Known Activations