© 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. 84964
    Prev
    Next
    INDEX
    Explanations

    repeated words followed by "of" or "and"

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

    This neuron identifies numeric tokens containing decimal points (fractional or precise measurements).

    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
     conocidos
    -1.13
    ществует
    -1.07
     sny
    -1.07
     твои
    -1.05
     мои
    -1.05
    语句
    -1.03
    闕
    -1.03
     saine
    -1.02
    やや
    -1.02
     Trou
    -1.02
    POSITIVE LOGITS
    سجيل
    1.36
     Ahora
    1.27
     eigentlichen
    1.27
     modalités
    1.23
     teratur
    1.20
    meneu
    1.20
     memutus
    1.20
    ("")]
    
    1.19
    ecznie
    1.19
    licans
    1.17
    Activations Density 0.012%

    No Known Activations