© 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. 12170
    Prev
    Next
    INDEX
    Explanations

    numbers, code, and punctuation

    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
    1.61
     .
    1.43
     -
    1.38
     –
    1.30
     [
    1.29
     ,
    1.26
    <sup>
    1.26
     (
    1.25
     @
    1.25
     Alternative
    1.24
    POSITIVE LOGITS
     ragazza
    1.74
     doença
    1.72
     crianças
    1.71
     chuva
    1.71
     aeropuerto
    1.68
     água
    1.63
     turistas
    1.60
     ragazzo
    1.60
     doenças
    1.59
     mulheres
    1.58
    Activations Density 0.045%

    No Known Activations