© 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. 199620
    Prev
    Next
    INDEX
    Explanations

    randomized studies

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

    cmd or command prompt

    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
     /
    0.54
     threatened
    0.51
    轴
    0.50
     zal
    0.49
     lant
    0.47
     zullen
    0.47
     dor
    0.46
    也有
    0.46
     <
    0.46
     Threatened
    0.45
    POSITIVE LOGITS
    iosas
    0.52
    thirds
    0.51
     टे
    0.50
    año
    0.50
    calcular
    0.49
    awks
    0.49
    tareas
    0.49
    anio
    0.49
    ात
    0.48
    obbly
    0.48
    Activations Density 0.003%

    No Known Activations