© 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. 74678
    Prev
    Next
    INDEX
    Explanations

    second quarter

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

    softness blooming; lips descended; it felt

    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
    崦
    0.51
     пыта
    0.49
     История
    0.49
     Викто
    0.48
     ร
    0.48
     نحاول
    0.47
     तरीका
    0.47
     ไง
    0.46
    {!
    0.46
     оконча
    0.46
    POSITIVE LOGITS
     draws
    0.57
     academies
    0.55
    em
    0.53
     being
    0.49
     drew
    0.49
    um
    0.49
    可在
    0.47
     BEING
    0.46
     progeny
    0.46
    的
    0.45
    Activations Density 0.001%

    No Known Activations