© 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. 164311
    Prev
    Next
    INDEX
    Explanations

    Pepsi, each time

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

    ball lightning, Macbook Pro

    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
    Ц
    0.61
    Ł
    0.54
    Ни
    0.53
    aft
    0.50
    О
    0.50
     pointless
    0.49
    }");
    0.48
    したがって
    0.48
    İ
    0.48
    На
    0.47
    POSITIVE LOGITS
    дев
    0.51
    ก่
    0.45
     eerder
    0.45
     المالية
    0.45
     heller
    0.45
     تحفظ
    0.45
    тной
    0.44
     bättre
    0.43
    嫦
    0.43
     perempuan
    0.42
    Activations Density 0.001%

    No Known Activations