© 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-65K
    7. 63132
    Prev
    Next
    INDEX
    Explanations

    morning, negative, filter, blue, seeing

    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
     discrepancy
    0.45
    IDUAL
    0.45
     mutex
    0.43
     atyp
    0.43
     polyd
    0.43
    ｿ
    0.43
    カス
    0.42
     tentativo
    0.42
     hepat
    0.42
     insidious
    0.42
    POSITIVE LOGITS
    ваем
    0.48
    ujemy
    0.47
     próxima
    0.46
     próximos
    0.44
    盔
    0.44
    ujących
    0.43
     đúng
    0.42
    ếu
    0.42
    给
    0.42
    ?",
    0.41
    Activations Density 0.008%

    No Known Activations