© 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. 6252
    Prev
    Next
    INDEX
    Explanations

    code delimiters or programming constructs

    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
    for
    0.27
    from
    0.27
    -
    0.26
    се
    0.25
    the
    0.25
    The
    0.24
    ट
    0.23
    first
    0.23
     The
    0.23
    p
    0.23
    POSITIVE LOGITS
     söyledi
    0.29
     chied
    0.26
     glauben
    0.25
     aplicar
    0.24
     banter
    0.24
     dishonest
    0.24
     ayatan
    0.23
     chival
    0.23
    件事情
    0.23
     scritto
    0.22
    Activations Density 0.076%

    No Known Activations