© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 98898
    Prev
    Next
    INDEX
    Explanations

    model identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     گیا۔
    0.46
     Verwendung
    0.40
    дится
    0.39
    পি
    0.37
    ódio
    0.37
    блі
    0.37
    ються
    0.37
    സ
    0.36
     sucesión
    0.36
    жом
    0.36
    POSITIVE LOGITS
     ,
    0.46
    ));
    0.40
     ),
    0.37
     فإن
    0.36
     academia
    0.36
    tor
    0.36
     )),
    0.35
    lang
    0.35
     encontrarás
    0.35
    .,
    0.34
    Activations Density 0.004%

    No Known Activations