© 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. 203182
    Prev
    Next
    INDEX
    Explanations

    case names and locations

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

    generator, equipment, writing

    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
    せた
    0.49
    ↵
    0.48
    Serve
    0.46
    ೆಯ
    0.45
     murine
    0.45
     serve
    0.43
     discussion
    0.43
     refining
    0.42
     ref
    0.42
     weights
    0.42
    POSITIVE LOGITS
    柺
    0.49
     khử
    0.46
     بدء
    0.45
    aha
    0.44
     tét
    0.44
     Unterschied
    0.44
    পথ
    0.44
    änn
    0.43
     الحد
    0.43
     appré
    0.43
    Activations Density 0.001%

    No Known Activations