© 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. 22-GEMMASCOPE-RES-131K
    7. 65090
    Prev
    Next
    INDEX
    Explanations

    table headers and data

    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
     salade
    -1.16
     patin
    -1.15
    Зміст
    -1.15
    nyv
    -1.14
     probably
    -1.14
     sopa
    -1.12
     supermercado
    -1.11
     chocolat
    -1.10
     sánchez
    -1.09
     carnaval
    -1.09
    POSITIVE LOGITS
     !!!!
    1.26
     VERY
    1.23
     astonishing
    1.19
     astounding
    1.16
     NEW
    1.15
    whats
    1.14
     gigantic
    1.13
    <mask>
    1.13
     mediocre
    1.13
    ギュ
    1.11
    Activations Density 0.000%

    No Known Activations