© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35624
    Prev
    Next
    INDEX
    Explanations

    企业、行业、过程、人群

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    1.44
    s
    1.20
    ز
    1.20
     by
    1.11
    the
    1.09
    es
    1.05
    et
    1.02
     an
    1.02
    k
    1.01
     to
    0.98
    POSITIVE LOGITS
    λλά
    1.22
     khác
    1.17
     miał
    1.16
    ।
    1.13
     shampoos
    1.10
     ¿?
    1.09
     predeceased
    1.06
    입니다
    1.05
    。
    1.05
     đều
    1.04
    Activations Density 0.009%

    No Known Activations