© 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. 82
    Prev
    Next
    INDEX
    Explanations

    .com / website domains

    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
    0.89
    im
    0.71
    on
    0.68
    as
    0.68
    ata
    0.65
    abouts
    0.63
    cations
    0.63
    ó
    0.61
     to
    0.61
    iv
    0.59
    POSITIVE LOGITS
     mencegah
    0.59
     colaboradores
    0.56
     jangan
    0.55
     menyatakan
    0.54
     rabbi
    0.54
     dati
    0.54
     menyebut
    0.53
    Ⲣ
    0.53
     domenica
    0.53
     rispondere
    0.53
    Activations Density 0.234%

    No Known Activations