© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 33102
    Prev
    Next
    INDEX
    Explanations

    driver, wallet, grid, synth options

    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
    研究
    0.46
    精准
    0.44
     делу
    0.41
     Fools
    0.40
    _{+
    0.38
    Science
    0.37
     цу
    0.37
     빠르게
    0.37
    灭
    0.37
     аутох
    0.37
    POSITIVE LOGITS
    isinin
    0.44
     demander
    0.42
     claves
    0.42
     xpath
    0.42
     constraint
    0.41
    谿
    0.41
    نر
    0.40
     modal
    0.40
     ert
    0.40
     fondamental
    0.40
    Activations Density 0.001%

    No Known Activations