© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 227993
    Prev
    Next
    INDEX
    Explanations

    project planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ling
    0.46
    Preparing
    0.44
     careful
    0.43
     preparing
    0.43
    сная
    0.42
     sapi
    0.42
    яс
    0.42
    ।
    0.41
    сное
    0.40
     inoculum
    0.40
    POSITIVE LOGITS
    ISTR
    0.55
     Bure
    0.48
    鑣
    0.48
     Конгрегация
    0.48
     Cronin
    0.48
    寻
    0.48
    genCode
    0.47
     FOUR
    0.47
     Supremo
    0.46
     ஐந்து
    0.46
    Activations Density 0.001%

    No Known Activations