© 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. 5958
    Prev
    Next
    INDEX
    Explanations

    linked websites or contexts

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

    this paragraph, god, before sunset

    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
    Е
    0.62
    對
    0.60
    З
    0.57
    Ç
    0.55
     Chiefs
    0.52
    ４
    0.50
    碼
    0.50
    Ở
    0.50
    FORT
    0.50
     FAMILY
    0.50
    POSITIVE LOGITS
    textured
    0.51
    اویر
    0.49
    niers
    0.48
     encompassing
    0.46
     مرت
    0.46
     decaying
    0.45
    fraud
    0.45
    newMessage
    0.45
     epit
    0.45
    errorMessage
    0.45
    Activations Density 0.000%

    No Known Activations