© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11705
    Prev
    Next
    INDEX
    Explanations

    for loops

    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
    <start_of_image>
    1.13
    ioned
    1.12
    ub
    1.11
    as
    1.08
    ha
    1.07
    og
    1.05
    qu
    1.04
    andu
    1.01
    in
    1.01
    <eos>
    0.99
    POSITIVE LOGITS
    𒁁
    1.76
    ꪽ
    1.76
    𒃲
    1.75
    𒈪
    1.74
    ࢯ
    1.73
    𒋫
    1.73
    𒄖
    1.72
    𒈥
    1.71
    𒊓
    1.69
    𒌒
    1.69
    Activations Density 0.004%

    No Known Activations