© 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. 6934
    Prev
    Next
    INDEX
    Explanations

    argument name completion

    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
    ちゃん
    0.90
    くん
    0.72
    /
    0.69
     (
    0.66
     свобод
    0.65
     Proc
    0.64
     /
    0.64
    さん
    0.63
    ,
    0.63
    準
    0.62
    POSITIVE LOGITS
    anagram
    1.52
    implemented
    1.29
     disgruntled
    1.28
     anagram
    1.26
     tangy
    1.25
    <unused625>
    1.25
    <unused1098>
    1.24
    <unused627>
    1.23
     rtn
    1.23
    <unused1910>
    1.23
    Activations Density 0.074%

    No Known Activations