© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22459
    Prev
    Next
    INDEX
    Explanations

    x1, x2, 1, 2

    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_10/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
     знают
    -1.35
    (){
    -1.31
     deseos
    -1.30
     acuerdos
    -1.28
     całej
    -1.26
     swoich
    -1.26
     peores
    -1.25
     mogę
    -1.24
     szczeg
    -1.23
     verdaderos
    -1.22
    POSITIVE LOGITS
    '
    1.29
    "
    1.29
    春天
    1.17
    STRO
    1.15
    ;
    1.14
    冬天
    1.10
    フィ
    1.10
     diejenigen
    1.09
    ši
    1.09
     findest
    1.09
    Activations Density 0.026%

    No Known Activations