© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9730
    Prev
    Next
    INDEX
    Explanations

    get up and running

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

    Rust match statements

    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_40_width_16k_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
    淍
    0.47
    スイッチ
    0.41
     ジョ
    0.40
     schak
    0.40
    Switch
    0.40
     République
    0.39
    ッシュ
    0.38
    訨
    0.38
     apellido
    0.38
     setError
    0.38
    POSITIVE LOGITS
     match
    1.07
    match
    1.05
     Match
    0.73
    Match
    0.68
    MATCH
    0.66
     MATCH
    0.66
    let
    0.62
    匹配
    0.60
     मैच
    0.60
     matches
    0.59
    Activations Density 0.002%

    No Known Activations