© 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. 68826
    Prev
    Next
    INDEX
    Explanations

    numbers between 0 and 9

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

    The main thing this neuron does is detect standalone numeric tokens (numbers and numeric literals) 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
     pensamientos
    -1.09
    <blockquote>
    -1.02
    }_{
    -1.00
     souvent
    -1.00
     {
    -0.99
     jednej
    -0.98
     a
    -0.98
    Fleur
    -0.97
    一旁
    -0.95
     eenige
    -0.95
    POSITIVE LOGITS
    Wady
    1.24
    与此同时
    1.18
    茘
    1.17
    ścić
    1.15
    Beskrivning
    1.15
    Beskrivelse
    1.13
    作り方
    1.10
    Significado
    1.06
    Alamat
    1.05
    ランキング
    1.05
    Activations Density 0.030%

    No Known Activations