© 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. 40-GEMMASCOPE-2-RES-262K
    7. 168462
    Prev
    Next
    INDEX
    Explanations

    combining concepts or actions

    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_40_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
    淳
    0.42
     годах
    0.41
    ánicas
    0.40
     barbaric
    0.39
    ्राम
    0.39
    羪
    0.39
     нача
    0.37
    bottlecap
    0.37
     това
    0.37
    贿
    0.37
    POSITIVE LOGITS
     documenting
    0.45
     detectable
    0.44
     Ideally
    0.43
     дослі
    0.43
     documented
    0.43
     wèi
    0.42
     analysis
    0.42
     referencing
    0.41
     burn
    0.41
     ideally
    0.41
    Activations Density 0.002%

    No Known Activations