© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 97143
    Prev
    Next
    INDEX
    Explanations

    every two years

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

    Ender Dragon

    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
     Carrick
    0.46
    ;
    0.45
     sprzedaży
    0.44
     Greeley
    0.43
     بعض
    0.43
     Carlyle
    0.43
     Dray
    0.43
    vislosti
    0.43
     Dorchester
    0.42
     Huddersfield
    0.42
    POSITIVE LOGITS
     fluorine
    0.42
     sulfur
    0.41
    調整
    0.41
    珐
    0.41
     stabilité
    0.41
     てる
    0.40
    允許
    0.40
     sufrimiento
    0.39
     boron
    0.38
     開始
    0.38
    Activations Density 0.005%

    No Known Activations