© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2058
    Prev
    Next
    INDEX
    Explanations

    longer, larger, more

    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
     ର
    0.43
     ಮಾತ್ರ
    0.42
     passi
    0.40
     _{(
    0.38
    每月
    0.37
    ("(
    0.37
     फोर्थ
    0.37
     нет
    0.36
     যাবতীয়
    0.36
    {(-
    0.36
    POSITIVE LOGITS
     longer
    0.55
    example
    0.50
     উদাহরণ
    0.49
    expanded
    0.49
     увеличи
    0.49
     훨씬
    0.49
    훨
    0.49
     увеличения
    0.48
     expand
    0.48
     длин
    0.47
    Activations Density 0.000%

    No Known Activations