© 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. 113275
    Prev
    Next
    INDEX
    Explanations

    subtotal, subtropical, Sudoku, reclamation

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

    The neuron selectively activates on the term “subtropical,” typically in ecological or habitat descriptions.

    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
     When
    -2.33
    喾
    -2.20
     It
    -2.14
    </i>
    -2.13
     عندما
    -2.08
    ࿙
    -2.06
    𖣘
    -2.05
     This
    -2.05
    驒
    -2.03
    ############
    -2.02
    POSITIVE LOGITS
    ↵
    2.22
     ‘
    2.22
    ↵↵
    2.11
    ’
    2.08
     roomy
    2.08
    for
    2.03
    sometimes
    1.88
    1
    1.86
     {
    1.80
    嫆
    1.80
    Activations Density 0.002%

    No Known Activations