© 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. 168255
    Prev
    Next
    INDEX
    Explanations

    time, got, should, auto, has, IP, military

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

    handling resize events

    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
     de
    0.52
     gear
    0.45
     and
    0.45
     decon
    0.44
    er
    0.44
     hatch
    0.44
    :
    0.44
     in
    0.43
    af
    0.42
     carefully
    0.42
    POSITIVE LOGITS
    윕
    0.47
    AnimationClip
    0.47
     ۸
    0.45
    Celltype
    0.45
     officielles
    0.44
    بلی
    0.44
     दमखम
    0.44
    ParentElement
    0.44
    Methylsulfanyl
    0.44
    モンスター
    0.43
    Activations Density 0.003%

    No Known Activations