© 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. 111784
    Prev
    Next
    INDEX
    Explanations

    gift ideas

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

    how things are done safely or exploitatively

    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
     Superintend
    0.49
    녔
    0.49
     EQUIPMENT
    0.49
     heuristics
    0.48
     betroffen
    0.47
    ,
    0.46
     rohkem
    0.45
    льники
    0.44
    رد
    0.44
     asem
    0.44
    POSITIVE LOGITS
    idez
    0.52
     हेल्दी
    0.48
    美食
    0.48
     fright
    0.47
    acate
    0.47
    C
    0.47
    ac
    0.47
    gana
    0.47
     अनावश्यक
    0.46
     宝宝
    0.46
    Activations Density 0.001%

    No Known Activations