© 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. 34-GEMMASCOPE-RES-131K
    7. 4129
    Prev
    Next
    INDEX
    Explanations

    languages names

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

    This neuron detects tokens containing numeric digits (i.e. numbers, version or year strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    rably
    -1.01
     μὲν
    -0.98
     Για
    -0.95
     aware
    -0.89
    chst
    -0.88
    睒
    -0.85
    atase
    -0.85
    ELSE
    -0.84
     its
    -0.84
    SizedBox
    -0.84
    POSITIVE LOGITS
     pelea
    0.98
    ån
    0.95
     skilful
    0.93
    警惕
    0.90
     mediodía
    0.88
    selben
    0.85
     eliminare
    0.84
     salvare
    0.83
     límite
    0.83
     alojamiento
    0.83
    Activations Density 0.005%

    No Known Activations