© 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. 99520
    Prev
    Next
    INDEX
    Explanations

    course, potential, line, pursue, estuarine

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

    Establish ground rules, walk regularly, interfaces

    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
     reforma
    0.52
     رہا
    0.50
     regering
    0.49
    াল
    0.45
    𝖾
    0.45
     rester
    0.44
     फायदा
    0.44
     spoonful
    0.43
    ELDS
    0.42
     จังหวัด
    0.42
    POSITIVE LOGITS
     простых
    0.47
    stm
    0.47
    мет
    0.44
     વા
    0.43
    swith
    0.43
    ]*
    0.43
    ț
    0.43
    ба
    0.43
    ıs
    0.42
    cz
    0.42
    Activations Density 0.000%

    No Known Activations