© 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. 172614
    Prev
    Next
    INDEX
    Explanations

    distinguish each

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

    open-weights

    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
    Regulation
    0.47
     নিয়ম
    0.45
    LN
    0.45
    лина
    0.44
     cleanliness
    0.44
     Regulation
    0.44
    ة
    0.43
    Secondary
    0.42
    regulation
    0.42
    醯
    0.42
    POSITIVE LOGITS
     zwią
    0.54
     emig
    0.49
     elde
    0.48
     tampil
    0.48
     społ
    0.47
     encomendas
    0.46
     najbardziej
    0.45
     médiocrement
    0.45
     mídia
    0.45
     ingenious
    0.45
    Activations Density 0.001%

    No Known Activations