© 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. 193655
    Prev
    Next
    INDEX
    Explanations

    scholarships or other awards

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

    but those, function defined

    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
     effet
    0.49
    ٹ
    0.46
    aundice
    0.46
     intractable
    0.46
    Celltype
    0.45
    reliability
    0.44
    ية
    0.44
     exercice
    0.44
     sunscreen
    0.43
     infertility
    0.43
    POSITIVE LOGITS
    m
    0.43
    Open
    0.43
     Diplom
    0.43
     Grows
    0.42
     сотрудник
    0.42
    Ian
    0.42
     scholarships
    0.41
    Ofer
    0.41
     дополнительные
    0.41
    रान
    0.40
    Activations Density 0.006%

    No Known Activations