© 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. 211076
    Prev
    Next
    INDEX
    Explanations

    upper extremity orthopedic

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

    seven Nepali girls

    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
    ታዊ
    0.48
     intervención
    0.47
     SaaS
    0.46
    Backup
    0.46
     expenditure
    0.45
    ా
    0.45
    ों
    0.45
    𒆳
    0.45
     Paleo
    0.44
    Meh
    0.44
    POSITIVE LOGITS
     moreover
    0.49
    cfe
    0.43
    uc
    0.43
    صد
    0.41
    বে
    0.40
    fv
    0.40
    el
    0.40
     matières
    0.40
    il
    0.39
    ypes
    0.39
    Activations Density 0.001%

    No Known Activations