© 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. 41002
    Prev
    Next
    INDEX
    Explanations

    always followed by verb

    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
    なく
    1.34
    comes
    1.32
    ↵↵
    1.30
    쨰
    1.30
     siquiera
    1.29
     tuyển
    1.28
     Atth
    1.27
     언제
    1.24
    Да
    1.21
     Plenty
    1.20
    POSITIVE LOGITS
    ت
    1.92
    ます
    1.70
    する必要
    1.40
    `${
    1.39
    못
    1.38
    ள்ளார்
    1.30
    ること
    1.29
    ين
    1.25
    rition
    1.23
    ný
    1.22
    Activations Density 0.017%

    No Known Activations