© 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. 35045
    Prev
    Next
    INDEX
    Explanations

    URL parts and code snippets

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

    The neuron fires on numeric tokens—i.e. it detects numbers or digit sequences 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
    ilibre
    -1.06
     What
    -0.95
     vitales
    -0.93
     شهرد
    -0.92
     They
    -0.91
     también
    -0.89
    URLConnection
    -0.88
    itchfield
    -0.86
    修士
    -0.84
     sagde
    -0.83
    POSITIVE LOGITS
     APPELLANT
    1.02
     bénévoles
    0.98
     nodig
    0.95
    ació
    0.93
     pełni
    0.91
    colgante
    0.91
    tou
    0.91
    Té
    0.91
    回来了
    0.90
    gefunden
    0.90
    Activations Density 0.007%

    No Known Activations