© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76686
    Prev
    Next
    INDEX
    Explanations

    "subject to", "change in", "fits your", "groups/classes", "as expected"

    np_acts-logits-general · gemini-2.5-flash-lite

    favorite comfort food, group fitness classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    m
    0.50
    an
    0.50
    c
    0.49
     AOC
    0.47
    𝙘
    0.47
    ab
    0.47
     Rosenberg
    0.46
    la
    0.46
    is
    0.45
    lly
    0.43
    POSITIVE LOGITS
     функції
    0.52
    사항
    0.47
    喡
    0.47
     маслом
    0.45
     Οι
    0.44
    菄
    0.44
     駅
    0.44
    ナソニック
    0.43
     بث
    0.43
    靝
    0.43
    Activations Density 0.001%

    No Known Activations