© 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-16K
    7. 8797
    Prev
    Next
    INDEX
    Explanations

    white words

    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_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
    Left
    0.44
    s
    0.44
     мали
    0.43
    купно
    0.42
     юго
    0.42
     накло
    0.41
    沇
    0.40
    แนว
    0.40
    sunset
    0.40
     яго
    0.40
    POSITIVE LOGITS
     white
    1.76
    white
    1.62
    白
    1.50
     fehér
    1.48
    白的
    1.45
     सफेद
    1.43
     beyaz
    1.43
     White
    1.41
    WHITE
    1.41
     সাদা
    1.40
    Activations Density 0.461%

    No Known Activations