© 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. 172271
    Prev
    Next
    INDEX
    Explanations

    bypass screen / S8 / Mi 8

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

    if... youpredicting path

    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
     शंक
    0.54
    radle
    0.49
    бна
    0.47
    𝐣
    0.44
     исто
    0.43
     कालेज
    0.43
    ﺯ
    0.43
    抚
    0.43
    킁
    0.43
    ጠን
    0.43
    POSITIVE LOGITS
     NEO
    0.52
     Calculate
    0.47
     calculate
    0.44
    ബു
    0.44
     YOLO
    0.43
     SQL
    0.42
     predict
    0.41
     perkara
    0.41
     transmit
    0.41
     Shooting
    0.41
    Activations Density 0.001%

    No Known Activations