© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2594
    Prev
    Next
    INDEX
    Explanations

    negative numbers and operations

    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_7_width_16k_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
    ोरेशन
    2.72
    ꗥ
    2.70
    𒈬
    2.69
    fnamefont
    2.67
    <unused569>
    2.66
     HTMLSc
    2.65
    <unused1203>
    2.65
    ЛА
    2.63
     văn
    2.62
    쮿
    2.61
    POSITIVE LOGITS
    ass
    1.71
    ek
    1.60
    /−
    1.59
    oon
    1.52
     dro
    1.50
    at
    1.47
    0
    1.47
    ,
    1.45
    /+
    1.44
    une
    1.44
    Activations Density 0.074%

    No Known Activations