© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 213693
    Prev
    Next
    INDEX
    Explanations

    HTML container div

    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
     nameWithOwner
    0.43
    癮
    0.42
    ništva
    0.40
    rollerskates
    0.39
    सव
    0.39
    汰
    0.39
    णुओं
    0.38
    鮭
    0.38
    ᄍ
    0.38
     جز
    0.38
    POSITIVE LOGITS
    -
    0.55
     first
    0.48
     und
    0.46
    ()-
    0.44
     K
    0.44
     cursor
    0.42
     gee
    0.41
     b
    0.41
    gee
    0.41
     prop
    0.41
    Activations Density 0.001%

    No Known Activations