© 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. 68526
    Prev
    Next
    INDEX
    Explanations

    at best, at least, at worst

    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
     échanti
    -1.16
    osten
    -1.11
     vakantie
    -1.09
     spesifik
    -1.09
     ſeveral
    -1.09
     himſelf
    -1.08
     izan
    -1.06
     vestidos
    -1.06
     tamaños
    -1.05
    apparently
    -1.04
    POSITIVE LOGITS
     a
    1.32
     an
    1.27
    至少
    1.21
     can
    1.19
     semi
    1.17
     mildly
    1.15
     two
    1.13
     put
    1.11
     B
    1.10
     will
    1.10
    Activations Density 0.015%

    No Known Activations