© 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. 34-GEMMASCOPE-RES-131K
    7. 116411
    Prev
    Next
    INDEX
    Explanations

    file extensions

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

    The neuron strongly activates on tokens containing digits (i.e. numeric strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     interpretations
    -0.79
    Dest
    -0.78
     Bundes
    -0.76
    ליה
    -0.73
    ाष
    -0.73
    AMPLES
    -0.72
     bú
    -0.72
     breaker
    -0.71
    Breaker
    -0.71
    uent
    -0.70
    POSITIVE LOGITS
     extension
    1.45
     extensions
    1.30
     strtolower
    1.18
     ".
    1.17
     Extension
    1.13
     '.
    1.11
    ('.'
    1.09
    +'.
    1.07
    Extensions
    1.05
     suffix
    1.05
    Activations Density 0.016%

    No Known Activations