© 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-262K
    7. 204838
    Prev
    Next
    INDEX
    Explanations

    18th century phrasing

    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_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
    V
    0.45
    Green
    0.44
    The
    0.40
    D
    0.40
    H
    0.40
    Drag
    0.39
    ह
    0.39
    External
    0.39
    IPA
    0.38
    웰
    0.38
    POSITIVE LOGITS
     Translational
    0.55
     Neuros
    0.51
    摖
    0.50
     alimentação
    0.49
     Serviço
    0.49
     Posterior
    0.48
     Sensor
    0.48
     Newborn
    0.48
     Nutrition
    0.47
     Physiology
    0.47
    Activations Density 0.005%

    No Known Activations