© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31868
    Prev
    Next
    INDEX
    Explanations

    answer all

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

    Honestly, and exclamations

    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_262k_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
     حی
    0.44
    idea
    0.44
    bona
    0.43
    nah
    0.41
    seat
    0.41
    bea
    0.41
    ‭
    0.41
    indicator
    0.40
    ibel
    0.39
     سرا
    0.39
    POSITIVE LOGITS
    汶
    0.52
    చిన
    0.51
    χρι
    0.51
    บค้น
    0.49
     chiffon
    0.48
    विधि
    0.47
    डून
    0.46
     endeavors
    0.46
    ọi
    0.46
    γραφή
    0.46
    Activations Density 0.000%

    No Known Activations