© 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. 68723
    Prev
    Next
    INDEX
    Explanations

    annual events and timeframes

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

    quantities and measurements

    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
    rali
    0.48
    ilem
    0.46
     fift
    0.44
     iż
    0.44
    楖
    0.44
    ifle
    0.43
    efeu
    0.42
    最新的
    0.42
    가격
    0.41
     jazdy
    0.41
    POSITIVE LOGITS
    ారు
    0.48
     साथी
    0.48
     средствами
    0.48
     увла
    0.46
     த
    0.46
     cytoskeleton
    0.46
     chất
    0.45
     gravedad
    0.45
    geht
    0.45
     その
    0.45
    Activations Density 0.002%

    No Known Activations