© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105405
    Prev
    Next
    INDEX
    Explanations

    noradrenergic neurons and ovulation

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

    scientific terms related to neurology, hormones, and biological processes, particularly those ending in "-ergic".

    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
    ?”
    -3.09
     condicionado
    -2.86
    rugada
    -2.64
    ).”
    -2.61
    .“
    -2.58
     (“
    -2.45
    鋮
    -2.39
    ”.
    -2.38
    —”
    -2.33
    -“
    -2.33
    POSITIVE LOGITS
     "
    3.08
    d
    3.03
    ING
    2.55
     linke
    2.38
    .
    2.36
    ه
    2.31
    洇
    2.30
     BOTH
    2.22
    かっこ
    2.22
     skvě
    2.19
    Activations Density 0.066%

    No Known Activations