© 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. 40-GEMMASCOPE-2-RES-262K
    7. 24324
    Prev
    Next
    INDEX
    Explanations

    white color in css

    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_40_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
     `#
    0.44
    =#
    0.41
     '#'
    0.41
    adika
    0.40
    忖
    0.39
     chromos
    0.38
     "#
    0.38
     radix
    0.38
     '#
    0.36
     #'
    0.36
    POSITIVE LOGITS
     white
    0.49
     fehér
    0.49
     beyaz
    0.44
    白
    0.44
     trắng
    0.43
     Wyd
    0.42
    白色
    0.41
     белый
    0.41
    white
    0.41
     blanco
    0.41
    Activations Density 0.005%

    No Known Activations