© 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. 130683
    Prev
    Next
    INDEX
    Explanations

    foreign words and general items

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

    what i need from

    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
    engono
    0.49
    녔
    0.47
    relatively
    0.46
     நேரடியாக
    0.46
     ಯು
    0.46
    МИ
    0.45
    蟻
    0.45
    дентификаторы
    0.45
    ovenant
    0.45
    ANCIS
    0.45
    POSITIVE LOGITS
     doprav
    0.53
     bonnes
    0.47
     pastime
    0.46
     stopp
    0.44
     ład
    0.44
     និង
    0.44
     schönen
    0.43
     attentions
    0.43
    、
    0.43
     bohat
    0.42
    Activations Density 0.001%

    No Known Activations