© 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. 142936
    Prev
    Next
    INDEX
    Explanations

    custom lists

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

    concepts and states

    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
     diminue
    0.49
     compl
    0.46
    larınız
    0.45
    끔
    0.44
     szczegól
    0.44
     collectif
    0.43
     społec
    0.43
    !';
    0.43
    Formatter
    0.43
     găsit
    0.43
    POSITIVE LOGITS
    agun
    0.52
    regnum
    0.48
    custom
    0.47
     precincts
    0.47
    ᱖
    0.46
    kb
    0.46
    ugo
    0.46
    heb
    0.46
     Aiden
    0.46
    ugg
    0.45
    Activations Density 0.000%

    No Known Activations