© 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. 179558
    Prev
    Next
    INDEX
    Explanations

    technological

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

    stolen ||| targeted ||| Wade

    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
     أيضًا
    0.48
    ন্তর
    0.41
     Moderate
    0.41
     Political
    0.41
    apps
    0.41
    asp
    0.40
    WM
    0.40
    Ứ
    0.40
     Applications
    0.40
     Operator
    0.40
    POSITIVE LOGITS
     vanes
    0.48
     则
    0.48
     excised
    0.47
    indazole
    0.47
     времени
    0.47
     หลาย
    0.47
    産
    0.46
     часу
    0.45
     дете
    0.45
     попыта
    0.45
    Activations Density 0.001%

    No Known Activations