© 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. 127325
    Prev
    Next
    INDEX
    Explanations

    multilingual phrases

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

    coding scheme, paid options, when possible

    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
     (
    0.43
    翮
    0.42
    о
    0.41
    ப்பின்
    0.40
     dépl
    0.40
     Debbie
    0.40
     sequence
    0.39
    撃
    0.39
    in
    0.39
    by
    0.39
    POSITIVE LOGITS
    গ্রামী
    0.48
    araan
    0.48
     jakiś
    0.48
     عنها
    0.47
     المثلثيه
    0.47
     jäl
    0.45
     kmeans
    0.45
     daleko
    0.45
    रियर
    0.45
     ಜನ
    0.45
    Activations Density 0.003%

    No Known Activations