© 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. 31489
    Prev
    Next
    INDEX
    Explanations

    seeds and spores

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

    disjunction or signals

    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
    מס
    0.43
    від
    0.42
     실제로
    0.40
    실
    0.40
    Д
    0.39
     components
    0.39
    克斯
    0.39
    В
    0.38
    אי
    0.38
    רה
    0.38
    POSITIVE LOGITS
     Tint
    0.45
    setBadgeText
    0.44
     Nano
    0.43
     UnitTest
    0.43
     Enables
    0.41
     Tattoo
    0.40
     Nên
    0.40
    mh
    0.40
     નક્કી
    0.39
     Regex
    0.39
    Activations Density 0.001%

    No Known Activations