© 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. 163373
    Prev
    Next
    INDEX
    Explanations

    identification

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

    states or conditions

    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
     Grundlage
    0.54
     많
    0.52
     Jej
    0.52
     ഘ
    0.51
     שב
    0.48
    䄸
    0.47
     令
    0.47
     เนื่อง
    0.47
    抽取
    0.46
    ன்ஹீ
    0.46
    POSITIVE LOGITS
     identific
    0.51
    ۔
    0.50
    ului
    0.45
     identification
    0.44
    לח
    0.44
    हिट
    0.43
     identifik
    0.43
    。（
    0.43
     идентифика
    0.42
     %>
    0.42
    Activations Density 0.000%

    No Known Activations