© 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. 11625
    Prev
    Next
    INDEX
    Explanations

    interactions and complexity

    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
    는
    0.68
     것은
    0.66
     wszystko
    0.66
    らは
    0.66
     вообще
    0.61
     संभव
    0.60
    是我们
    0.60
     뭐
    0.60
     أيضا
    0.60
    は大
    0.59
    POSITIVE LOGITS
    ot
    0.71
    as
    0.70
    and
    0.69
    ate
    0.66
    from
    0.66
    it
    0.66
    ou
    0.65
    idences
    0.65
    opies
    0.64
    sourced
    0.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.