© 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. 109833
    Prev
    Next
    INDEX
    Explanations

    temporal sequences and associated actions

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

    security and privacy

    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
    নি
    0.57
    ↵
    0.50
    r
    0.47
     Publications
    0.46
     Virtual
    0.45
     Yacht
    0.44
    虚拟
    0.44
    <b>
    0.44
    winner
    0.44
    ana
    0.43
    POSITIVE LOGITS
     schop
    0.45
    ција
    0.43
     armado
    0.43
     часу
    0.42
     buffered
    0.41
     agrícola
    0.40
     земель
    0.40
     elevates
    0.40
     badass
    0.40
     estaría
    0.40
    Activations Density 0.000%

    No Known Activations