© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62155
    Prev
    Next
    INDEX
    Explanations

    multiple requirements or legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    쉬
    0.50
    편
    0.50
    수
    0.48
    ت
    0.48
    ed
    0.46
    シナ
    0.46
    후
    0.45
    slope
    0.45
    ルド
    0.44
    Ꮞ
    0.44
    POSITIVE LOGITS
     tätig
    0.55
     Begriff
    0.47
     politič
    0.46
     obowią
    0.46
     transmitted
    0.46
     certaines
    0.46
    บาง
    0.46
    GraphicsUnit
    0.45
     політи
    0.44
     cursus
    0.44
    Activations Density 0.032%

    No Known Activations