© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133118
    Prev
    Next
    INDEX
    Explanations

    economy opportunity

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

    paid services or visits

    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
    getImageFolder
    0.52
    カメラ
    0.50
    இவ்வாறு
    0.48
     vendeur
    0.46
    𓏧
    0.46
     comerciantes
    0.45
    酊
    0.45
    ውነ
    0.44
    ਤਾ
    0.44
     nourrice
    0.44
    POSITIVE LOGITS
    hers
    0.55
    euros
    0.54
     Eds
    0.54
    bies
    0.46
     relegated
    0.46
    quest
    0.46
    iley
    0.46
    buster
    0.46
    bs
    0.45
     indicates
    0.45
    Activations Density 0.000%

    No Known Activations