© 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-16K
    7. 7193
    Prev
    Next
    INDEX
    Explanations

    exploring or sourcing concepts

    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_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
     boolean
    0.49
     trusty
    0.47
     curvature
    0.46
     soup
    0.45
     kernel
    0.44
    య
    0.44
     softmax
    0.43
     web
    0.43
     odds
    0.43
     harmonica
    0.43
    POSITIVE LOGITS
    ča
    0.54
    tugraz
    0.52
    legg
    0.50
     Анаста
    0.48
    čo
    0.47
    ɟ
    0.47
    aría
    0.47
    erent
    0.46
    attham
    0.46
    WITT
    0.46
    Activations Density 0.070%

    No Known Activations