© 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. 90992
    Prev
    Next
    INDEX
    Explanations

    "and" context, "weather", "better way", "layer", "expression", "Dijkstra"

    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
     fibrosis
    0.45
    forRoot
    0.41
     base
    0.40
     initially
    0.40
    reson
    0.39
    য়ে
    0.38
    stimulation
    0.38
    ຮ
    0.37
    scaron
    0.37
    core
    0.37
    POSITIVE LOGITS
    𝙖
    0.51
     అ
    0.45
    ንም
    0.45
     терро
    0.45
     Picture
    0.45
    偻
    0.44
     ഒരു
    0.44
     ఒక
    0.44
     వద్ద
    0.43
     ஒரு
    0.43
    Activations Density 0.007%

    No Known Activations