© 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-65K
    7. 3150
    Prev
    Next
    INDEX
    Explanations

    HTML/XML character entities

    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_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
    |-\
    0.43
    DIST
    0.39
    Spending
    0.39
    風味
    0.38
    0.36
    เซล
    0.36
     عوامل
    0.36
    ॥
    0.35
    牝
    0.34
    contain
    0.34
    POSITIVE LOGITS
     nbsp
    0.73
    nbsp
    0.70
    ccedil
    0.67
     "&#
    0.67
    eacute
    0.63
    hellip
    0.62
    aacute
    0.61
    ">&
    0.61
    szlig
    0.59
     &#
    0.58
    Activations Density 0.031%

    No Known Activations