© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100201
    Prev
    Next
    INDEX
    Explanations

    exogenous or endogenous factors

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

    The neuron detects words related to biological origins, particularly "endogenous" and "exogenous" in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron flags occurrences of the scientific terms “endogenous” and “exogenous.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     This
    -3.36
     
    -2.72
     Some
    -2.50
    2
    -2.50
     {
    -2.44
     THE
    -2.30
     Our
    -2.30
     the
    -2.25
    —
    -2.22
    -2.20
    POSITIVE LOGITS
    硨
    2.66
    🢒
    2.50
    Ꮏ
    2.39
     époque
    2.38
     greateſt
    2.31
     CascadeType
    2.31
     etek
    2.30
     expérience
    2.28
    　　-
    2.28
    
    2.27
    Activations Density 0.008%

    No Known Activations