© 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. 16-GEMMASCOPE-2-RES-16K
    4. 15254
    Prev
    Next
    INDEX
    Explanations

    driving letter ranges

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

    letters associated with numbers

    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_16_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
     i
    0.63
    i
    0.62
    ı
    0.62
     Defensa
    0.59
    the
    0.57
    1
    0.55
    boo
    0.54
    </i>
    0.54
    2
    0.52
     C
    0.52
    POSITIVE LOGITS
    ﮕ
    0.67
     در
    0.65
     انگیز
    0.61
     étamines
    0.59
     effetto
    0.57
    likle
    0.55
     имат
    0.55
     доба
    0.55
     invers
    0.55
     گئیں
    0.55
    Activations Density 0.035%

    No Known Activations