© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200010
    Prev
    Next
    INDEX
    Explanations

    warranties, manuals, expense, authorization

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

    authorization, preauthorization, card, surge

    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
    䡒
    0.55
    व्य
    0.52
    Collectors
    0.48
    劷
    0.47
    圻
    0.47
    𝐰
    0.46
     अहि
    0.46
    AMOUNT
    0.46
    )^{-\
    0.46
    หรือไม่
    0.45
    POSITIVE LOGITS
     manuals
    0.66
     authorization
    0.57
     retrograde
    0.56
     magnes
    0.55
     watches
    0.55
     composite
    0.54
     be
    0.54
     most
    0.52
     breakthroughs
    0.52
     nebul
    0.51
    Activations Density 0.000%

    No Known Activations