© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 61
    Prev
    Next
    INDEX
    Explanations

    programming tools and concepts

    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_12_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
    in
    0.82
    し
    0.71
    I
    0.71
    न
    0.69
    在
    0.68
    A
    0.68
    G
    0.67
    мум
    0.67
    농
    0.67
    ছেন
    0.66
    POSITIVE LOGITS
     publicados
    0.77
     reembolso
    0.72
     наличии
    0.71
     نے
    0.70
     sanciones
    0.70
    ี
    0.65
     Plaintiffs
    0.63
    seiten
    0.63
     beinhaltet
    0.63
     kasutada
    0.63
    Activations Density 0.137%

    No Known Activations