© 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. 46646
    Prev
    Next
    INDEX
    Explanations

    Japan

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

    creating, shrunk, ability

    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
    含量
    0.51
    螅
    0.47
    krét
    0.46
    總
    0.46
    越來越
    0.46
    ong
    0.45
    etri
    0.45
    лянчук
    0.45
    ety
    0.45
     linguistics
    0.44
    POSITIVE LOGITS
    م
    0.61
    糀
    0.53
    ס
    0.52
    Configuration
    0.50
    ว
    0.49
    м
    0.47
     Principal
    0.47
    ות
    0.46
    Japan
    0.46
    އ
    0.46
    Activations Density 0.000%

    No Known Activations