© 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. 105296
    Prev
    Next
    INDEX
    Explanations

    reservior Dogs, inquiry, resolution passed

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

    water and moisture sensors

    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
    re
    0.55
     கூட
    0.50
     പോലും
    0.48
    akte
    0.47
    ve
    0.47
    y
    0.46
     tattoos
    0.46
    werden
    0.46
     cookies
    0.45
    kontrol
    0.44
    POSITIVE LOGITS
     ঘনিষ্ঠ
    0.46
     sahabat
    0.46
     transformación
    0.46
     showbiz
    0.45
    ˮ
    0.45
     socialista
    0.44
     vínculo
    0.42
     познакоми
    0.42
    ക്കാല
    0.42
     LGB
    0.42
    Activations Density 0.002%

    No Known Activations