© 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. 50462
    Prev
    Next
    INDEX
    Explanations

    new or when

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

    new when

    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
     শব্দটি
    0.49
    に関する
    0.46
    によっては
    0.45
     রাজনৈতিক
    0.45
    얽
    0.45
     capitalist
    0.44
    金融
    0.44
     capitalism
    0.44
     procedural
    0.43
    岌
    0.43
    POSITIVE LOGITS
     nowych
    0.55
     když
    0.52
     nuevas
    0.51
     nuove
    0.50
     nových
    0.50
     neuen
    0.48
     Když
    0.48
     quando
    0.48
    幼稚園
    0.47
     cuando
    0.46
    Activations Density 0.000%

    No Known Activations