© 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. 11472
    Prev
    Next
    INDEX
    Explanations

    definition and datasets

    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
    exercitos
    1.91
    쮿
    1.88
    positroids
    1.86
    totalts
    1.86
    𒅤
    1.86
    𒃷
    1.85
    𒊍
    1.85
    स्मैपदी
    1.85
    퍁
    1.85
    𒐖
    1.85
    POSITIVE LOGITS
    ;
    1.09
     created
    1.09
     and
    1.09
    (
    1.08
    :
    0.97
     (
    0.97
     implemented
    0.97
    able
    0.96
    ar
    0.96
    ,
    0.95
    Activations Density 0.000%

    No Known Activations