© 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. 156439
    Prev
    Next
    INDEX
    Explanations

    professional and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    or safety or even

    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
    shovel
    0.45
     struggle
    0.45
    ային
    0.43
    GISLATIVE
    0.43
    column
    0.43
     ሳይ
    0.42
    text
    0.42
    չ
    0.41
     mush
    0.41
     ಹೃ
    0.41
    POSITIVE LOGITS
     मरीजों
    0.51
     Atty
    0.47
     виды
    0.47
     traverses
    0.46
     চক
    0.46
    ्रा
    0.46
     probabilidades
    0.45
     opiek
    0.45
     sported
    0.45
     canales
    0.45
    Activations Density 0.001%

    No Known Activations