© 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. 3509
    Prev
    Next
    INDEX
    Explanations

    quantifiers and additions

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

    sections, folders, formulas, contexts

    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
    т
    0.52
    “
    0.52
    t
    0.49
    ，“
    0.48
    ments
    0.48
    h
    0.47
    fib
    0.47
    strings
    0.46
    hashMap
    0.46
    bans
    0.46
    POSITIVE LOGITS
     STYLE
    0.49
     marchio
    0.49
     सेक्शन
    0.48
    뽐
    0.48
     CABINET
    0.47
     belle
    0.46
     MAGNET
    0.44
     légende
    0.43
     पाव
    0.43
     FRANCE
    0.43
    Activations Density 0.000%

    No Known Activations