© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13131
    Prev
    Next
    INDEX
    Explanations

    reporting speech attribution

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

    The neuron activates strongly on tokens that are purely numeric (digits), i.e. it detects numbers or numerical figures 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
     that
    -1.10
    Specyfikacja
    -0.96
     dzied
    -0.91
    怎么办
    -0.90
    objets
    -0.88
     музея
    -0.88
     энциклопедия
    -0.88
    idées
    -0.87
    ıyors
    -0.87
    sellors
    -0.86
    POSITIVE LOGITS
     yesterday
    1.07
    mindedness
    1.06
    ivity
    1.05
    lables
    1.02
     シー
    1.01
     اللاعب
    1.01
     旅游
    0.97
    Mask
    0.96
     pelbagai
    0.94
    aritions
    0.94
    Activations Density 0.009%

    No Known Activations