© 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. 241428
    Prev
    Next
    INDEX
    Explanations

    .au links and comments

    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
    pe
    0.56
    cop
    0.52
    作
    0.48
    м
    0.48
    本当
    0.47
    本土
    0.46
    co
    0.46
    е
    0.44
    工業
    0.44
    濟
    0.44
    POSITIVE LOGITS
    alakip
    0.60
     συ
    0.50
     εξε
    0.50
     approached
    0.50
     glared
    0.48
     वेरिएबल
    0.48
     ascended
    0.47
     gasped
    0.47
    ."},
    0.46
     ব্যস্ত
    0.46
    Activations Density 0.001%

    No Known Activations