© 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. 6507
    Prev
    Next
    INDEX
    Explanations

    about/nearly followed by numbers

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

    quantifiable results by number

    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
    占
    0.42
    用的
    0.40
     половине
    0.40
    VARIABLE
    0.40
     Pathway
    0.39
     Бере
    0.38
    としての
    0.38
     Clustering
    0.38
     VARIABLE
    0.38
    emale
    0.37
    POSITIVE LOGITS
     twofold
    0.73
     threefold
    0.70
     tenfold
    0.66
    幅度
    0.65
    almost
    0.55
     (+
    0.55
    大幅
    0.54
     leaps
    0.54
     fold
    0.53
     YoY
    0.53
    Activations Density 0.072%

    No Known Activations