© 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. 169601
    Prev
    Next
    INDEX
    Explanations

    code imports and dependencies

    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
     Trustees
    0.45
     Supervisors
    0.43
     HTMLSc
    0.43
    calaureate
    0.42
     Entomology
    0.42
     Hydrochloride
    0.41
     Profesor
    0.41
    《
    0.41
     Artistic
    0.41
     Pilates
    0.41
    POSITIVE LOGITS
     madrid
    0.70
     barcelona
    0.70
     josé
    0.67
     méxico
    0.66
     david
    0.63
     michael
    0.63
     antonio
    0.62
     bmw
    0.60
     yamaha
    0.60
     pvc
    0.60
    Activations Density 0.572%

    No Known Activations