© 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. 183583
    Prev
    Next
    INDEX
    Explanations

    your options or choice

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

    good decision

    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
     motif
    0.50
     mechanism
    0.48
     sniper
    0.48
     infantry
    0.47
     café
    0.47
     ポ
    0.46
     plaza
    0.46
     stove
    0.45
     وح
    0.45
     bü
    0.45
    POSITIVE LOGITS
    Exper
    0.47
    Careers
    0.46
     DETERMIN
    0.45
    кме
    0.43
    ᱘
    0.43
     futuros
    0.43
     Flutter
    0.43
    ﺏ
    0.43
    Factors
    0.42
    Всім
    0.42
    Activations Density 0.001%

    No Known Activations