© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166642
    Prev
    Next
    INDEX
    Explanations

    sports substitutions

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

    criminalized, vaccinated, learning curves

    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
    Negative Logits
    एएस
    0.46
    carbons
    0.42
    也不能
    0.41
    碳
    0.41
     বরাদ্দ
    0.40
     त्यावर
    0.39
    夙
    0.39
     flotte
    0.39
    愎
    0.39
    ктери
    0.38
    POSITIVE LOGITS
    ły
    0.55
    walking
    0.47
    čili
    0.47
    li
    0.47
    रि
    0.46
    shaped
    0.46
     छ
    0.45
    án
    0.44
    ৫
    0.44
    song
    0.43
    Activations Density 0.000%

    No Known Activations