© 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. 109484
    Prev
    Next
    INDEX
    Explanations

    official document signatures and places

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

    sequences that precede specific punctuation or words

    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
     bronchi
    0.42
    ⏬
    0.41
     आतंकवादी
    0.40
    Menu
    0.40
    edk
    0.39
     fusion
    0.38
    menu
    0.37
     لیک
    0.37
    residential
    0.37
    ándola
    0.36
    POSITIVE LOGITS
     Medizin
    0.50
     các
    0.48
     ancienne
    0.47
    ט
    0.46
     էր
    0.46
     Jeux
    0.45
     Ét
    0.45
    реа
    0.45
     да
    0.45
    рда
    0.44
    Activations Density 0.001%

    No Known Activations