© 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-16K
    7. 76
    Prev
    Next
    INDEX
    Explanations

    that are characteristics

    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_16k_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
     That
    1.56
    That
    1.56
    And
    1.52
     입니다
    1.46
    ・
    1.45
    でした
    1.44
    Doing
    1.43
     ataupun
    1.43
    之
    1.43
    ＆
    1.43
    POSITIVE LOGITS
     transcends
    1.39
     underlies
    1.31
     characterizes
    1.30
     governs
    1.25
     encompasses
    1.23
     accompanies
    1.23
     adheres
    1.22
     differs
    1.22
     regulates
    1.21
     distinguishes
    1.21
    Activations Density 1.109%

    No Known Activations