© 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. 134853
    Prev
    Next
    INDEX
    Explanations

    remembered, award, Architecture

    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
     Nordic
    0.51
     redistribution
    0.47
     Scandinavian
    0.46
    多い
    0.45
    がつ
    0.43
     ない
    0.42
     landowner
    0.42
     {
    0.42
     nordic
    0.41
    ある
    0.41
    POSITIVE LOGITS
     кирпи
    0.55
    प्ली
    0.47
    回忆
    0.47
    పథ
    0.45
     policías
    0.45
    抖音
    0.45
    fangs
    0.45
    constant
    0.44
     आजही
    0.43
     జ్ఞాప
    0.43
    Activations Density 0.003%

    No Known Activations