© 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. 175579
    Prev
    Next
    INDEX
    Explanations

    plurality of votes

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

    number of

    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
     row
    0.53
     V
    0.52
     pays
    0.52
     rumble
    0.50
     zoom
    0.48
     wav
    0.48
     Quil
    0.48
     reden
    0.47
     vocal
    0.47
     sel
    0.47
    POSITIVE LOGITS
     زيت
    0.55
    ftan
    0.50
    ovariant
    0.50
     ಅಧಿಕ
    0.49
    ieft
    0.49
    diamine
    0.48
    氫
    0.47
    timevals
    0.47
    ut
    0.47
    apayati
    0.47
    Activations Density 0.001%

    No Known Activations