© 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. 87603
    Prev
    Next
    INDEX
    Explanations

    not in

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

    membership testing with 'in'

    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
    ĝo
    0.54
    дом
    0.49
    віда
    0.48
    鹊
    0.47
    сида
    0.46
    ąp
    0.46
    ınca
    0.46
    ше
    0.45
    羡慕
    0.45
    ца
    0.44
    POSITIVE LOGITS
     freeway
    0.52
     杯
    0.49
     nowhere
    0.49
     Ư
    0.46
    %
    0.46
    vic
    0.45
     Bereich
    0.45
     rapids
    0.45
    left
    0.44
     dentre
    0.44
    Activations Density 0.001%

    No Known Activations