Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3371
    Prev
    Next
    INDEX
    Explanations

    first, Cleveland, Number, end, Play

    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
     and
    0.88
     gaat
    0.85
     not
    0.85
     har
    0.69
    дает
    0.69
    <0x0D>
    0.68
     demais
    0.64
     rot
    0.64
     mais
    0.63
     rada
    0.62
    POSITIVE LOGITS
    ␊
    1.84
    ›
    1.74
    hetiti
    1.73
    ichromo
    1.72
    ṓ
    1.72
    𐰃
    1.70
    .",[
    1.69
     \\..
    1.69
     threx
    1.66
     iccad
    1.65
    Activations Density 0.286%

    No Known Activations