© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10346
    Prev
    Next
    INDEX
    Explanations

    brain and brain areas

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

    brain structures and neural processes

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

    brain

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    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
     Polaroid
    0.45
     furnishing
    0.40
    💄
    0.40
     ब्रैकेट
    0.40
     furnish
    0.39
     foodservice
    0.38
     Flush
    0.38
     Oils
    0.38
    蟎
    0.38
    酯
    0.37
    POSITIVE LOGITS
     brain
    1.61
    大脑
    1.48
    脳
    1.48
    脑
    1.46
    brain
    1.41
    Brain
    1.40
     Brain
    1.38
     मस्तिष्क
    1.33
     моз
    1.32
     brains
    1.30
    Activations Density 0.195%

    No Known Activations