© 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. 39080
    Prev
    Next
    INDEX
    Explanations

    yeast or encoder

    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
     sociaux
    0.89
    benhav
    0.81
     ""<
    0.79
    vať
    0.79
     ámbito
    0.77
     excepciones
    0.77
    триму
    0.76
     livello
    0.74
    द्योगिक
    0.74
     infancia
    0.74
    POSITIVE LOGITS
    ра
    1.13
    ת
    1.04
    ing
    1.03
    ون
    1.03
    р
    1.02
    ل
    0.91
    out
    0.90
    in
    0.90
    ung
    0.89
    কে
    0.88
    Activations Density 0.001%

    No Known Activations