© 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. 3539
    Prev
    Next
    INDEX
    Explanations

    different ways of being

    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
    /
    1.06
    ment
    1.06
     and
    1.05
    ,
    1.03
    ments
    0.97
    an
    0.95
    .
    0.95
    enche
    0.93
    -
    0.91
    o
    0.90
    POSITIVE LOGITS
     şeyi
    1.47
     früheren
    1.36
     şey
    1.34
     Bakın
    1.29
     sayıda
    1.29
    ὗ
    1.23
     klassischen
    1.22
     damals
    1.21
     jongens
    1.20
     verschillende
    1.19
    Activations Density 0.103%

    No Known Activations