© 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. 1115
    Prev
    Next
    INDEX
    Explanations

    variations, dance, planner, feathered, habilis, new

    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
    e
    0.74
    t
    0.72
    g
    0.71
    es
    0.70
    un
    0.67
    i
    0.67
    l
    0.66
    en
    0.65
    s
    0.65
    in
    0.64
    POSITIVE LOGITS
     berühm
    1.06
    Très
    1.04
    Namun
    1.03
    આ
    1.02
    Deux
    1.02
    تاب
    1.02
    Dalam
    1.02
    İlk
    1.02
    ╴
    1.01
    Secondo
    1.01
    Activations Density 0.575%

    No Known Activations