© 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. 81262
    Prev
    Next
    INDEX
    Explanations

    architectural styles and locations

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

    understand the formula

    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
    試合
    0.51
     ramach
    0.46
    סה
    0.45
     obecnie
    0.45
    畋
    0.45
    oncesto
    0.45
    ここまで
    0.45
    拯
    0.44
    认可
    0.43
    Remote
    0.43
    POSITIVE LOGITS
     electrification
    0.56
     clots
    0.54
    ights
    0.53
    ~~
    0.53
    buds
    0.52
     lures
    0.52
     allotments
    0.51
    ~
    0.51
     restorations
    0.51
     installations
    0.50
    Activations Density 0.000%

    No Known Activations