© 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. 69755
    Prev
    Next
    INDEX
    Explanations

    American history, wash it, consumer and, spent Rs, is able

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

    relatively easy or simple

    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
    散射
    0.46
    担当
    0.46
    Crawler
    0.45
     Khartoum
    0.45
    1
    0.45
    サイズ
    0.43
    LocalAppData
    0.43
    Москва
    0.43
     Fallout
    0.42
    ʲ
    0.42
    POSITIVE LOGITS
    genomen
    0.44
    钀
    0.44
     egos
    0.44
     expon
    0.43
    ego
    0.42
     संचालक
    0.41
    둰
    0.41
    钰
    0.40
    gran
    0.40
     актива
    0.39
    Activations Density 0.001%

    No Known Activations