© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68866
    Prev
    Next
    INDEX
    Explanations

    mixed code and descriptive text

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

    The neuron activates on numeric tokens, i.e. it detects standalone numbers.

    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
     &=&
    -1.15
     !!}
    -1.15
    👫
    -1.13
     Mérimée
    -1.10
    schöne
    -1.09
    ❣
    -1.09
    🌳
    -1.07
    ❕
    -1.07
    👶
    -1.06
    äfts
    -1.05
    POSITIVE LOGITS
    ,
    1.15
    o
    1.09
     erstmal
    0.99
    iz
    0.95
    e
    0.93
    j
    0.90
    ilding
    0.89
    ot
    0.88
     v
    0.87
     something
    0.85
    Activations Density 0.000%

    No Known Activations