© 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. 188228
    Prev
    Next
    INDEX
    Explanations

    foreign words and symbols

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

    algebraic reasoning and websockets

    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
    ,
    0.52
     into
    0.47
     nac
    0.45
    ion
    0.45
    ende
    0.44
    obed
    0.44
     අධ
    0.43
    AM
    0.43
     ina
    0.42
    diameter
    0.42
    POSITIVE LOGITS
    летка
    0.50
    ','"
    0.50
    싣
    0.46
    꿉
    0.46
     ಬಿಜೆ
    0.45
    
    0.45
     게임
    0.45
    chodzi
    0.45
    мат
    0.44
    бит
    0.44
    Activations Density 0.001%

    No Known Activations