© 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. 219691
    Prev
    Next
    INDEX
    Explanations

    worth investing

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

    product/vein/code/potential

    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
    barn
    0.48
    နှ
    0.47
     nă
    0.46
     張
    0.46
    w
    0.46
     ပြော
    0.45
     Paperback
    0.45
     Jang
    0.45
     l
    0.44
     ám
    0.44
    POSITIVE LOGITS
    Worlds
    0.56
    ETO
    0.51
    घु
    0.50
    Ethoxy
    0.50
    Layers
    0.48
    лета
    0.48
    ETE
    0.48
    Lato
    0.48
    That
    0.47
    ลิ
    0.47
    Activations Density 0.000%

    No Known Activations