© 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. 23476
    Prev
    Next
    INDEX
    Explanations

    el Prince

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

    Robb Stark, divValue, SQL, open source

    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
     Challenges
    0.59
     Challenge
    0.56
     Pain
    0.52
     challenges
    0.51
     X
    0.50
     Life
    0.50
     Health
    0.50
     Un
    0.50
     Panel
    0.50
     Office
    0.49
    POSITIVE LOGITS
    🥸
    0.55
     resumen
    0.52
    뭍
    0.49
    🥶
    0.48
    🫰
    0.48
    ياه
    0.47
    лого
    0.47
     postaci
    0.46
    ARAJYA
    0.46
    🫣
    0.46
    Activations Density 0.000%

    No Known Activations