© 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. 188163
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    likely or rarely followed by completion

    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
    xiety
    0.46
    </
    0.44
    nof
    0.44
     ベージュ
    0.43
     screamed
    0.43
     flattering
    0.42
     whistling
    0.42
    undant
    0.42
     ಗ್ರಾಮ
    0.41
    morning
    0.41
    POSITIVE LOGITS
     инстру
    0.64
    欵
    0.54
    弦
    0.52
     ву
    0.48
    加大
    0.48
     मिळणार
    0.48
    скому
    0.47
    чек
    0.47
    метка
    0.46
     Benutz
    0.46
    Activations Density 0.000%

    No Known Activations