© 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
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 422
    Prev
    Next
    INDEX
    Explanations

    two things being compared

    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_24_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
    udrait
    0.80
    3
    0.79
    5
    0.75
     diferente
    0.71
    4
    0.71
    2
    0.69
    7
    0.69
    ized
    0.68
     batas
    0.68
    ’
    0.68
    POSITIVE LOGITS
     sexes
    1.24
    ان
    0.96
     sides
    0.91
    uah
    0.89
     halves
    0.84
    u
    0.84
    ти
    0.84
     पक्षों
    0.80
     genders
    0.78
    тись
    0.78
    Activations Density 0.012%

    No Known Activations