© 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. 99198
    Prev
    Next
    INDEX
    Explanations

    ESC, terms, birds, blog, goes, websites, words, entities

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

    speech danger

    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
    ј
    0.51
    transactions
    0.47
    responsive
    0.47
    ales
    0.45
    orders
    0.45
    congestion
    0.43
    income
    0.42
    alkyl
    0.42
    答
    0.41
    order
    0.41
    POSITIVE LOGITS
     baptized
    0.51
     Athena
    0.50
     projekt
    0.49
    িলিয়া
    0.49
     Polytechn
    0.48
     Infrast
    0.48
     ئێ
    0.48
     Leibnitz
    0.47
    vVertex
    0.47
     nebude
    0.46
    Activations Density 0.001%

    No Known Activations