© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24530
    Prev
    Next
    INDEX
    Explanations

    magic mushrooms or tracers

    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
    🐟
    0.54
     fisherman
    0.50
     catfish
    0.49
     fish
    0.48
     fished
    0.48
     fisheries
    0.47
    鱼
    0.46
    魚
    0.46
    釣り
    0.45
     underwater
    0.45
    POSITIVE LOGITS
    кци
    0.44
     Static
    0.42
     Goni
    0.41
    窸
    0.39
     Nation
    0.39
    RPC
    0.38
     sobering
    0.38
     static
    0.38
    static
    0.38
     Reef
    0.37
    Activations Density 0.007%

    No Known Activations