© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 32780
    Prev
    Next
    INDEX
    Explanations

    global scope and static variables

    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
    nage
    0.43
    ക്കോ
    0.41
     rép
    0.40
    pmatrix
    0.40
     ceremonial
    0.39
    cję
    0.39
     ceremonies
    0.39
    |.|.|
    0.38
     nouvelle
    0.38
     новую
    0.38
    POSITIVE LOGITS
     nonlocal
    0.63
    Global
    0.61
     Global
    0.54
     глоба
    0.52
    Scope
    0.51
    global
    0.51
     scopes
    0.51
    GLOBAL
    0.48
     Scope
    0.48
    地元
    0.48
    Activations Density 0.011%

    No Known Activations