© 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. 653
    Prev
    Next
    INDEX
    Explanations

    provides/provides a

    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
     avoir
    0.64
    AR
    0.63
    ){}^
    0.63
    ্দ্র
    0.61
     kB
    0.61
     propia
    0.61
     dañ
    0.61
     otras
    0.60
    s
    0.60
     retali
    0.59
    POSITIVE LOGITS
     insight
    0.88
     glimpse
    0.82
     enables
    0.79
    opportunity
    0.79
     позволяет
    0.78
    Provides
    0.76
     opportunity
    0.75
     Provides
    0.73
     सुविधा
    0.71
    opportunities
    0.71
    Activations Density 0.000%

    No Known Activations