© 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. 25556
    Prev
    Next
    INDEX
    Explanations

    words and phrases

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

    This neuron flags programmer‐defined identifiers (i.e. alphanumeric names of variables, constants, functions, etc.).

    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
     všechny
    -0.94
    ביו
    -0.94
    問題は
    -0.92
    ässä
    -0.91
     recupera
    -0.91
     foie
    -0.90
     Exteriores
    -0.90
    水彩
    -0.89
    這些
    -0.88
     palestra
    -0.87
    POSITIVE LOGITS
    It
    1.01
    同樣
    0.92
     also
    0.91
    J
    0.91
     نیز
    0.91
    AN
    0.89
    We
    0.88
     too
    0.87
    ON
    0.87
     праздника
    0.86
    Activations Density 0.018%

    No Known Activations