© 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. 15793
    Prev
    Next
    INDEX
    Explanations

    names, places, or actions

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

    | identifier | most, | 🖥️AI:

    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
     is
    1.31
     a
    1.10
     to
    1.08
    1.05
     使っ
    0.82
     (
    0.81
     \
    0.81
    ísim
    0.76
     =
    0.74
    п
    0.74
    POSITIVE LOGITS
    ق
    0.98
     for
    0.95
    for
    0.88
    น
    0.84
    us
    0.81
    ون
    0.80
    and
    0.80
    મ
    0.79
    و
    0.79
    u
    0.76
    Activations Density 3.620%

    No Known Activations