© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71922
    Prev
    Next
    INDEX
    Explanations

    other candidates, characters, others

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

    The neuron predominantly activates on numeric tokens (counts, percentages, and other numerical data) in the text.

    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
     its
    -1.30
     it
    -1.19
     atentos
    -0.93
     его
    -0.88
     meningkatkan
    -0.86
     только
    -0.86
     incluso
    -0.84
     requested
    -0.83
     tersebut
    -0.82
     physical
    -0.82
    POSITIVE LOGITS
     other
    2.27
     others
    1.70
     остальных
    1.70
    的其他
    1.62
     dalších
    1.59
    其他
    1.57
     autres
    1.56
     innych
    1.55
    อื่น
    1.55
     diğer
    1.51
    Activations Density 0.039%

    No Known Activations