© 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. 38967
    Prev
    Next
    INDEX
    Explanations

    start of descriptive phrases

    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
     what
    -1.31
     Tenemos
    -1.14
    ſer
    -1.12
     Prenez
    -1.12
     bezpośred
    -1.09
    >((
    -1.09
    rolex
    -1.07
     Cómo
    -1.07
    dekat
    -1.06
    =>$
    -1.05
    POSITIVE LOGITS
    ַּ
    1.50
    Ų
    1.21
    el
    1.10
     worin
    1.04
    ment
    1.04
    IZIONE
    1.03
    ֶּ
    1.02
    ūras
    1.02
     chén
    1.01
    ot
    1.00
    Activations Density 0.001%

    No Known Activations