© 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. 177265
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    local, closest, moment

    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
    河流
    0.45
    larının
    0.44
    **)
    0.42
    那些
    0.42
     aquellas
    0.42
    .),
    0.41
    ногие
    0.41
    inerja
    0.40
    ),
    0.40
     aqueles
    0.40
    POSITIVE LOGITS
     ispit
    0.43
     ತಿಳ
    0.42
    북도
    0.42
     ഇഷ്ട
    0.42
     resisting
    0.41
     faintly
    0.41
     괜찮
    0.40
     മി
    0.40
     ಬ
    0.39
     ගන්න
    0.39
    Activations Density 0.000%

    No Known Activations