© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 832
    Prev
    Next
    INDEX
    Explanations

    mathematical or grammatical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    ⊔
    2.13
     emoticon
    1.98
     emoji
    1.95
    redraw
    1.92
    ཋ
    1.91
     requester
    1.89
    painter
    1.87
     painter
    1.86
     packageName
    1.86
     né
    1.86
    POSITIVE LOGITS
    an
    1.23
     benefits
    1.08
     ventajas
    1.03
    ما
    0.95
    不断的
    0.91
     있는데요
    0.90
    शल
    0.89
    ماً
    0.89
    <h2>
    0.89
     maximum
    0.88
    Activations Density 0.000%

    No Known Activations