© 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. 73044
    Prev
    Next
    INDEX
    Explanations

    Results: followed by details

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

    The neuron is detecting numeric tokens (integers or decimals).

    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
     tiras
    -1.07
     flé
    -1.05
    scrapy
    -1.00
     fábricas
    -1.00
    啮
    -0.97
     holand
    -0.97
    ほうがいい
    -0.96
     hés
    -0.96
     betrug
    -0.95
     éta
    -0.94
    POSITIVE LOGITS
     to
    1.02
    7
    0.98
    man
    0.96
    (!_
    0.93
    Note
    0.93
    
    0.93
    CR
    0.91
    MAN
    0.90
    3
    0.90
    utils
    0.89
    Activations Density 0.005%

    No Known Activations