© 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. 34-GEMMASCOPE-RES-131K
    4. 98455
    Prev
    Next
    INDEX
    Explanations

    methods and delivery options

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

    The neuron strongly activates on tokens that express numeric quantities or list-like enumeration (e.g. counts, multipliers, or explicit 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_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
    動き
    -0.83
    тын
    -0.81
    amarca
    -0.81
    cmdline
    -0.76
    輟
    -0.73
    缇
    -0.72
    рюкзак
    -0.71
    リエ
    -0.70
    ndrome
    -0.70
    ASMA
    -0.69
    POSITIVE LOGITS
     methods
    3.41
     method
    3.11
    methods
    2.75
    Methods
    2.59
     método
    2.53
     Methods
    2.52
    method
    2.50
    方式
    2.47
     delivery
    2.41
    Method
    2.39
    Activations Density 0.163%

    No Known Activations