© 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. 134931
    Prev
    Next
    INDEX
    Explanations

    laws God, ceremony attended, from china, from industry, collection at

    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
    Cors
    0.45
    british
    0.43
    ፦
    0.42
    Brexit
    0.42
     britannique
    0.42
    Sport
    0.42
     نب
    0.41
     ریا
    0.41
    USES
    0.41
    떳
    0.41
    POSITIVE LOGITS
     ill
    0.49
    vaa
    0.46
    eman
    0.44
    iong
    0.44
    ama
    0.43
    illi
    0.43
    ilon
    0.42
     Eqs
    0.42
     MasterCard
    0.42
    indle
    0.42
    Activations Density 0.000%

    No Known Activations