© 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. 212730
    Prev
    Next
    INDEX
    Explanations

    new sentence beginnings

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

    following conjunctions and discourse markers

    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
     Luton
    0.48
     укреп
    0.48
     соціа
    0.47
     Guernsey
    0.47
    皖
    0.47
     socializing
    0.46
     Wilmington
    0.46
     social
    0.46
    进士
    0.45
     Derby
    0.45
    POSITIVE LOGITS
    cepat
    0.45
    ']['
    0.44
    bulan
    0.44
    یا
    0.43
    ASCADE
    0.43
    বাদের
    0.43
     Portanto
    0.43
     Monaten
    0.43
    ltal
    0.43
    stato
    0.43
    Activations Density 0.000%

    No Known Activations