© 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. 10-GEMMASCOPE-RES-131K
    4. 11265
    Prev
    Next
    INDEX
    Explanations

    academic addresses and locations

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

    The neuron activates on standalone numeric tokens (integers or decimals) in the text, i.e. it detects 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_10/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
     ruft
    -1.36
     two
    -1.33
     reigning
    -1.29
    <
    -1.27
     same
    -1.27
    savevideo
    -1.27
    standigheden
    -1.25
    ichert
    -1.21
     our
    -1.20
    пев
    -1.20
    POSITIVE LOGITS
     cyclisme
    1.28
    forderung
    1.26
    larını
    1.22
     canadienne
    1.19
     }(\
    1.16
     uygula
    1.16
     betaling
    1.15
    larına
    1.13
     jambe
    1.13
     andere
    1.12
    Activations Density 0.085%

    No Known Activations