© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111417
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases

    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_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
    :
    0.54
     Crem
    0.53
     Millie
    0.48
     Dispon
    0.47
     Sesame
    0.46
     Vibrant
    0.46
     Kraków
    0.46
     inoxydable
    0.45
     Din
    0.44
     Doyle
    0.44
    POSITIVE LOGITS
     잡아
    0.45
     группы
    0.44
    ifah
    0.43
    igel
    0.42
    ྐ
    0.42
    વાનું
    0.42
    itabbo
    0.42
     కలి
    0.41
    ωμα
    0.41
    눙
    0.41
    Activations Density 0.003%

    No Known Activations