© 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. 130853
    Prev
    Next
    INDEX
    Explanations

    Thai, Japanese, and Korean characters

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

    English sentences from tables

    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
    ק
    0.56
    لما
    0.55
    ضاف
    0.54
    画像の
    0.54
    ⱨ
    0.54
     kulland
    0.51
     планы
    0.50
    ালার
    0.50
     göstere
    0.50
     jelas
    0.50
    POSITIVE LOGITS
    .
    0.49
    ée
    0.44
    eness
    0.43
    えました
    0.43
    Buffers
    0.42
    OfThe
    0.41
    emen
    0.41
    eten
    0.41
    ための
    0.41
    の後
    0.41
    Activations Density 0.000%

    No Known Activations