© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46263
    Prev
    Next
    INDEX
    Explanations

    mathematical and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
     ಎರಡ
    0.54
    这两个
    0.46
     இரண்டாவது
    0.43
    *,
    0.43
     Kedua
    0.42
    两个
    0.41
    ặp
    0.41
     Both
    0.41
     Two
    0.40
     Beide
    0.40
    POSITIVE LOGITS
    ല്ലാം
    0.40
    icam
    0.40
     ade
    0.39
     arus
    0.39
    ppure
    0.37
    cion
    0.37
     ellas
    0.37
     mamma
    0.36
     灬
    0.36
    kon
    0.36
    Activations Density 0.124%

    No Known Activations