© 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. 22-GEMMASCOPE-RES-131K
    7. 15675
    Prev
    Next
    INDEX
    Explanations

    TEntity definitions

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

    The neuron fires strongly on PascalCase or ALL_CAPS identifiers—i.e. class, type, and other uppercase token names in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     BOTH
    -1.06
    homonymie
    -1.02
     M
    -0.94
     Name
    -0.94
    zeppelin
    -0.93
     „
    -0.92
     ‘
    -0.91
    разуме
    -0.91
     ALL
    -0.91
     THE
    -0.91
    POSITIVE LOGITS
    牴
    1.23
     acesta
    1.19
    Liet
    1.11
     mangiare
    1.10
     CALIF
    1.07
     этом
    1.05
    Тан
    1.03
    ība
    1.02
    ємо
    1.01
     requerida
    1.01
    Activations Density 0.005%

    No Known Activations