© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15848
    Prev
    Next
    INDEX
    Explanations

    measure and count

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

    measurements used

    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_31_width_16k_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
     तिथि
    0.60
    to
    0.59
     பெரும்
    0.59
    Datetime
    0.58
     ornamented
    0.57
    ು
    0.57
     अवलंब
    0.56
    uştur
    0.55
    toMap
    0.55
    extractor
    0.54
    POSITIVE LOGITS
    '
    0.99
     measure
    0.95
     Measure
    0.92
     misura
    0.91
     ölç
    0.86
     measurement
    0.85
     medir
    0.85
     măsur
    0.85
    MEAS
    0.83
     측정
    0.83
    Activations Density 1.042%

    No Known Activations