© 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. 155300
    Prev
    Next
    INDEX
    Explanations

    stronger than stuck

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

    foreign language words

    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
    pre
    0.51
    .
    0.47
    -
    0.47
    Winter
    0.47
    Garden
    0.47
    compl
    0.47
    ad
    0.46
    qu
    0.46
    Rah
    0.45
    Youth
    0.45
    POSITIVE LOGITS
    таль
    0.60
     связан
    0.54
    स्करण
    0.52
     графи
    0.52
     и
    0.50
     алюми
    0.50
     belladone
    0.49
    सेने
    0.49
     забруд
    0.49
     bør
    0.49
    Activations Density 0.000%

    No Known Activations