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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32032
    Prev
    Next
    INDEX
    Explanations

    french fries

    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_16_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
    нија
    0.67
    蓥
    0.65
    할
    0.61
     بيقول
    0.60
     at
    0.59
     upholstered
    0.58
    이는
    0.57
    Το
    0.57
    fulfilled
    0.57
     kneading
    0.57
    POSITIVE LOGITS
    is
    0.84
    and
    0.80
    ing
    0.79
    u
    0.79
    er
    0.72
     v
    0.68
    te
    0.68
    UMENT
    0.65
    ة
    0.65
    ma
    0.64
    Activations Density 0.002%

    No Known Activations