© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3317
    Prev
    Next
    INDEX
    Explanations

    We

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ни
    2.17
    ли
    1.91
    ди
    1.88
    ब
    1.69
    ا
    1.66
    ların
    1.64
    larını
    1.63
     elucid
    1.60
    ை
    1.60
    ك
    1.60
    POSITIVE LOGITS
    ção
    2.05
     Portanto
    1.58
    łego
    1.57
    contacto
    1.57
    ỏe
    1.53
    ⅼ
    1.52
    ism
    1.49
    து
    1.48
     Toutefois
    1.45
    chemical
    1.43
    Activations Density 0.127%

    No Known Activations