© 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. 70450
    Prev
    Next
    INDEX
    Explanations

    economiclegalgeographic

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

    microscopic structures, sexual shock, international transfers

    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
     stanje
    0.53
    Projectile
    0.50
    ชั้น
    0.49
     mouve
    0.49
    γε
    0.48
    Prz
    0.47
    鯵
    0.47
     nekaj
    0.46
    ϋ
    0.46
    ਉ
    0.46
    POSITIVE LOGITS
     Obtaining
    0.55
     Advocate
    0.49
     தலைமையில்
    0.49
     Advocates
    0.49
     Đình
    0.47
     ソフト
    0.47
     memperoleh
    0.46
     પ્રા
    0.45
     Hairst
    0.45
     obtaining
    0.45
    Activations Density 0.000%

    No Known Activations