© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7622
    Prev
    Next
    INDEX
    Explanations

    cases, expressions, cycle, water

    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
     consisting
    0.93
    /
    0.92
     whereupon
    0.91
     with
    0.91
     comprising
    0.86
     ngunit
    0.82
     pero
    0.82
     but
    0.81
     (
    0.80
     ranging
    0.77
    POSITIVE LOGITS
    以及
    0.81
     、,
    0.77
    、
    0.74
     zusätzlichen
    0.72
     sowie
    0.71
    、$
    0.66
    、“
    0.64
     以及
    0.64
     sekä
    0.64
     zusätzliche
    0.64
    Activations Density 0.081%

    No Known Activations