© 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. 24-GEMMASCOPE-2-RES-16K
    7. 611
    Prev
    Next
    INDEX
    Explanations

    route, multiplication, movement

    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_24_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
     mutilated
    0.42
     trifling
    0.38
     oatmeal
    0.38
     ២
    0.38
     ৩২
    0.36
     רא
    0.35
     ৩৩
    0.35
     oyster
    0.35
     verein
    0.35
     sabbatical
    0.35
    POSITIVE LOGITS
    of
    0.46
    it
    0.46
    。
    0.43
    It
    0.42
    aka
    0.42
    eng
    0.41
    だと
    0.40
    At
    0.40
    ก่อน
    0.39
    that
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.