© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6639
    Prev
    Next
    INDEX
    Explanations

    numbered lists or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     in
    0.61
     all
    0.61
     is
    0.60
     the
    0.59
     and
    0.57
     of
    0.57
     that
    0.57
    0.57
    ’
    0.54
     n
    0.53
    POSITIVE LOGITS
    ecção
    0.59
    atthena
    0.57
    iduci
    0.55
    ocsát
    0.54
    ließt
    0.54
    ämään
    0.54
    éseket
    0.54
    ዖ
    0.54
     dhinak
    0.53
    ethoscope
    0.53
    Activations Density 0.044%

    No Known Activations