© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    code structure or programming elements

    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
    images
    0.75
    ো
    0.72
    reme
    0.70
    대전
    0.69
    evice
    0.67
    пропетров
    0.66
     провели
    0.65
    صل
    0.64
    ples
    0.63
    Images
    0.63
    POSITIVE LOGITS
    𝜎
    0.76
     equating
    0.75
     Peut
    0.73
     complejos
    0.72
    स्तिष्क
    0.71
     blancas
    0.71
     LANC
    0.71
     comest
    0.70
    뒀
    0.70
     kyll
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.