© 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. 238203
    Prev
    Next
    INDEX
    Explanations

    language or origin identifiers

    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
    وح
    0.47
    rani
    0.46
    夊
    0.45
    sust
    0.44
     inqu
    0.43
    staben
    0.43
     despair
    0.43
    قر
    0.43
     marqu
    0.42
    tipo
    0.42
    POSITIVE LOGITS
    DOC
    0.53
     предше
    0.49
    6
    0.49
    DUT
    0.48
     ઘણા
    0.47
     Bangladeshi
    0.47
     മുന്‍
    0.47
     hadir
    0.47
     учеб
    0.46
     संलग्न
    0.45
    Activations Density 0.000%

    No Known Activations