© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9050
    Prev
    Next
    INDEX
    Explanations

    key postgraduate

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

    medical interventions

    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_40_width_16k_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
    戙
    0.54
    堣
    0.50
     दूरसंचार
    0.50
    🐢
    0.50
    棪
    0.50
     मोबाईल
    0.50
    📪
    0.49
    溦
    0.49
    㕣
    0.48
    涳
    0.47
    POSITIVE LOGITS
    ableness
    0.73
     sundry
    0.63
     peculiarly
    0.63
     bosom
    0.60
     achromatic
    0.60
     multitud
    0.58
     diminution
    0.57
     effectually
    0.57
     chiefly
    0.57
    eliness
    0.56
    Activations Density 0.713%

    No Known Activations