© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3428
    Prev
    Next
    INDEX
    Explanations

    nationalpark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    を追加
    1.22
    -
    1.18
    +
    1.17
     moreover
    1.16
    スペイン
    1.11
    +",
    1.08
    aden
    1.07
    hankelijk
    1.06
    在北京
    1.05
     copolymer
    1.02
    POSITIVE LOGITS
    ศ
    1.23
     Fid
    1.18
     Стра
    1.08
    sca
    1.05
     Swo
    1.05
     Stab
    1.02
     Timing
    1.02
     Stal
    1.01
     Bial
    1.00
    ירה
    0.99
    Activations Density 0.028%

    No Known Activations