© 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. 70785
    Prev
    Next
    INDEX
    Explanations

    complete with

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

    GABA production

    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
     agave
    0.50
     STADT
    0.49
     alasan
    0.48
     progetto
    0.47
     fondamental
    0.47
     contradd
    0.46
    喩
    0.46
     exfoliating
    0.46
     spazi
    0.46
     signage
    0.46
    POSITIVE LOGITS
    IC
    0.45
     ඉක්
    0.44
    G
    0.43
    对手
    0.43
     Certainly
    0.42
    C
    0.41
    MouseEnter
    0.41
    DW
    0.41
     Qualquer
    0.40
     Schüler
    0.40
    Activations Density 0.001%

    No Known Activations