© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3820
    Prev
    Next
    INDEX
    Explanations

    manner and degree

    np_acts-logits-general · gemini-2.5-flash-lite

    adverbs of manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    БК
    0.44
    ющиеся
    0.41
    ický
    0.40
    ដ៏
    0.40
    ập
    0.39
     ganske
    0.39
    裡的
    0.39
    <unused37>
    0.39
    lbrakk
    0.39
    вшийся
    0.38
    POSITIVE LOGITS
     enough
    0.95
    enough
    0.80
    ishly
    0.73
    ly
    0.72
    heartedly
    0.70
     genug
    0.67
    Enough
    0.66
    ingly
    0.66
     Enough
    0.65
    istically
    0.64
    Activations Density 0.276%

    No Known Activations