© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11348
    Prev
    Next
    INDEX
    Explanations

    discussion of

    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_16k_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
     dozen
    0.90
    huy
    0.82
    स्ताना
    0.77
     عشر
    0.76
    剐
    0.75
    あまり
    0.73
     मौजूदगी
    0.73
    होत
    0.72
    스트
    0.72
     относительно
    0.71
    POSITIVE LOGITS
    Ș
    0.81
     dijel
    0.80
    isce
    0.70
    OREM
    0.70
     volat
    0.69
    seur
    0.69
    SH
    0.68
     Règlement
    0.68
    俬
    0.68
     prejudicial
    0.67
    Activations Density 0.003%

    No Known Activations