© 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. 21544
    Prev
    Next
    INDEX
    Explanations

    breaking or split

    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
    𐐪
    -1.47
    They
    -1.41
    Also
    -1.37
     хвилин
    -1.37
    cestry
    -1.35
     '',
    -1.35
    werbe
    -1.35
    ayakan
    -1.34
    Antes
    -1.34
    銦
    -1.30
    POSITIVE LOGITS
     then
    1.35
     モン
    1.31
     its
    1.30
     drifting
    1.23
    tet
    1.21
     between
    1.20
     wenige
    1.18
     communis
    1.18
     маленький
    1.17
     principalmente
    1.16
    Activations Density 0.035%

    No Known Activations