© 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. 67465
    Prev
    Next
    INDEX
    Explanations

    places and specific nouns

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

    community where

    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
     虽然
    0.51
     Runway
    0.49
     生命周期
    0.48
    اری
    0.47
     Botanical
    0.47
     普通
    0.47
     TGC
    0.47
     သ
    0.46
     एक्सपे
    0.46
     Mathematical
    0.45
    POSITIVE LOGITS
    엿
    0.46
    лис
    0.44
    atz
    0.44
    РИ
    0.42
    한국
    0.42
    둣
    0.42
    人性
    0.41
    랴
    0.41
    암
    0.41
    opat
    0.41
    Activations Density 0.001%

    No Known Activations