© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6195
    Prev
    Next
    INDEX
    Explanations

    asking for clarification to help

    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_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
     বিদ্যুৎ
    1.72
    ಸ್ಕ
    1.67
    ｊ
    1.66
     مشینوں
    1.63
    imil
    1.55
     transference
    1.54
    ച്ചു
    1.54
     slowdown
    1.53
    ⌔
    1.53
    ीडियो
    1.52
    POSITIVE LOGITS
     Triangle
    1.78
    Case
    1.58
    CRE
    1.57
     треуго
    1.56
     Truss
    1.46
     угол
    1.45
     Trigon
    1.44
     Athlet
    1.42
     Case
    1.41
    তীত
    1.41
    Activations Density 0.148%

    No Known Activations