© 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. 11559
    Prev
    Next
    INDEX
    Explanations

    labeling and marking items

    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
     '\''
    2.91
     compartido
    2.72
     sguardo
    2.63
    ᱭ
    2.62
     //-->
    2.61
     suono
    2.60
    toHaveBeenCalled
    2.60
    ͹
    2.57
     ========
    2.55
    $^{
    2.53
    POSITIVE LOGITS
    er
    2.63
    erings
    2.50
    NewLabel
    2.47
    erate
    2.46
    მწიფ
    2.35
    acing
    2.17
     lö
    2.15
    TION
    2.13
    ing
    2.13
    ისუფ
    2.09
    Activations Density 0.390%

    No Known Activations