© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27337
    Prev
    Next
    INDEX
    Explanations

    codes and languages interleaved

    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
     or
    -1.20
     on
    -1.13
    loggen
    -1.02
    ᠢ
    -1.01
     epitom
    -0.96
    尽可能
    -0.96
     انتشار
    -0.95
     as
    -0.95
     Mith
    -0.93
     nobis
    -0.92
    POSITIVE LOGITS
     compromisso
    1.12
    asable
    1.10
     also
    1.09
    ?
    1.07
     anderes
    1.07
     vermittelt
    1.07
     orçamento
    1.07
     confiable
    1.06
     problemet
    1.04
    籏
    1.02
    Activations Density 0.001%

    No Known Activations