© 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. 153957
    Prev
    Next
    INDEX
    Explanations

    foreign language and phrases

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

    no problem

    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
    blackberry
    0.48
    SOLE
    0.46
    Million
    0.46
    ‹
    0.44
    raviolet
    0.44
    SCHRAMM
    0.44
    Despatx
    0.44
     stratégies
    0.43
    VISION
    0.43
    czki
    0.43
    POSITIVE LOGITS
     chez
    0.52
     y
    0.50
     a
    0.50
     c
    0.48
     di
    0.47
     či
    0.47
     aux
    0.47
     ac
    0.46
     vous
    0.46
     '
    0.45
    Activations Density 0.002%

    No Known Activations