© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1055
    Prev
    Next
    INDEX
    Explanations

    prefrontal cortex and frontal eye fields

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

    brain regions and neuroanatomical structures in scientific text, particularly those related to the prefrontal cortex, amygdala, and other brain areas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consentimiento
    -1.32
     a
    -1.30
    ("")
    
    -1.27
    us
    -1.26
    👫
    -1.24
     |
    
    -1.20
    ﹶ
    -1.18
    UREAU
    -1.16
    胪
    -1.16
     erhöhen
    -1.16
    POSITIVE LOGITS
     where
    1.50
    ↵
    1.48
    bersicht
    1.32
     escolas
    1.26
     ogranic
    1.25
    慵
    1.23
     narrowly
    1.22
     farmaco
    1.21
    汹
    1.20
     alguma
    1.19
    Activations Density 0.140%

    No Known Activations