© 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. 62013
    Prev
    Next
    INDEX
    Explanations

    future or soon

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

    significantly improved, On boarding, Offer Practical

    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
     climatic
    0.42
     resorption
    0.40
    品
    0.40
    চিত
    0.39
    是可以
    0.38
     EASY
    0.38
    調理
    0.38
     council
    0.38
     Kid
    0.38
     angegeben
    0.38
    POSITIVE LOGITS
    곧
    0.46
     곧
    0.46
     문제는
    0.44
     விரைவில்
    0.43
    फाई
    0.43
    尽快
    0.42
    亟
    0.42
     станет
    0.40
    ുണ്ട
    0.40
     شفاف
    0.40
    Activations Density 0.000%

    No Known Activations