© 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. 14258
    Prev
    Next
    INDEX
    Explanations

    renting

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

    programming and anatomy descriptions

    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
    IsNullOrEmpty
    0.45
    ukup
    0.43
    Dv
    0.42
    clen
    0.42
    longest
    0.42
    (=
    0.42
    ALBERT
    0.41
    ༨
    0.41
     ખે
    0.41
     रजिस्ट्री
    0.41
    POSITIVE LOGITS
     پشتی
    0.53
     pow
    0.50
     ủng
    0.49
     sürü
    0.48
    صميم
    0.47
     Pow
    0.46
    itores
    0.45
     місце
    0.44
     Dés
    0.44
     Đồng
    0.44
    Activations Density 0.009%

    No Known Activations