© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14998
    Prev
    Next
    INDEX
    Explanations

    abbreviations punctuated with periods

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

    {symbol} punctuation

    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
    8
    1.09
    7
    1.07
    4
    1.06
    3
    1.05
    6
    1.05
    5
    1.00
    9
    0.98
    ４
    0.73
    ６
    0.71
    ８
    0.69
    POSITIVE LOGITS
    u
    0.61
     ﺍ
    0.56
     costru
    0.54
    ו
    0.54
     posizione
    0.52
     "`
    0.50
    த்
    0.50
     realizzazione
    0.50
     त्वरित
    0.50
     ​​
    0.49
    Activations Density 0.418%

    No Known Activations