© 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. 133621
    Prev
    Next
    INDEX
    Explanations

    stock price targets

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

    room temperature eggs

    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
    敎
    0.54
    ঘ্র
    0.51
    왤
    0.47
     教
    0.46
     Брита
    0.46
     ክብ
    0.46
    Cabinet
    0.46
    ск
    0.46
     кө
    0.45
    кг
    0.45
    POSITIVE LOGITS
     Ramos
    0.49
     (
    0.46
    span
    0.46
    since
    0.46
     Ser
    0.46
     XX
    0.46
    fte
    0.46
     it
    0.45
    long
    0.45
     Mer
    0.45
    Activations Density 0.001%

    No Known Activations