© 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. 7074
    Prev
    Next
    INDEX
    Explanations

    variables and equations

    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
    ).”
    0.75
    leicht
    0.69
    REIB
    0.68
    וחות
    0.66
    ).)
    0.66
     effectuées
    0.66
     fréquentes
    0.66
    滪
    0.66
    អំ
    0.65
    patan
    0.64
    POSITIVE LOGITS
    '
    1.05
    ose
    0.99
    ’
    0.95
    iz
    0.92
    nd
    0.89
    í
    0.88
    ara
    0.86
    را
    0.86
    és
    0.84
    ri
    0.79
    Activations Density 1.781%

    No Known Activations