© 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. 188537
    Prev
    Next
    INDEX
    Explanations

    vehicles, with, URI, political, Staphylococcus, taller

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

    joke setup

    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
    r
    0.53
    Containing
    0.49
     Flowers
    0.49
    yourself
    0.46
     AST
    0.46
    everything
    0.45
    discovered
    0.45
     everything
    0.45
     Capitalism
    0.44
    ോട്ട്
    0.44
    POSITIVE LOGITS
    ִ
    0.50
     带
    0.49
     கிரேக்க
    0.48
     單
    0.46
     বিচার
    0.44
     gerade
    0.44
     उन्‍ह
    0.44
     μεταξύ
    0.44
    ρθ
    0.43
     దృష్టి
    0.43
    Activations Density 0.000%

    No Known Activations