© 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. 12133
    Prev
    Next
    INDEX
    Explanations

    numpy and python code

    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
    ádz
    1.57
    zynarod
    1.53
    <unused453>
    1.51
    ಲೆಂ
    1.49
    勮
    1.49
    zeptember
    1.47
    槤
    1.46
    તાં
    1.45
    𒌨
    1.45
    ibalsan
    1.44
    POSITIVE LOGITS
    ,
    1.14
    1
    1.00
     and
    0.98
    6
    0.95
    :
    0.94
     произ
    0.93
     This
    0.93
    ،
    0.91
    0
    0.91
    7
    0.87
    Activations Density 0.000%

    No Known Activations