© 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. 22-GEMMASCOPE-RES-131K
    4. 54028
    Prev
    Next
    INDEX
    Explanations

    technical type keywords

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

    The neuron activates on any token containing a digit (i.e. numerals or alphanumeric strings with 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_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
     this
    -1.25
     their
    -1.16
     what
    -1.15
     any
    -1.11
     unusually
    -1.09
     supremely
    -1.05
    〜。
    -1.05
     some
    -1.04
     providing
    -1.02
     surprisingly
    -1.02
    POSITIVE LOGITS
     PROFESSIONAL
    1.12
    #,
    1.10
     💕
    1.05
     composés
    1.05
    プリング
    1.05
    Vl
    1.02
     ché
    1.01
    ḿ
    0.99
     Chbosky
    0.99
    regardless
    0.98
    Activations Density 0.001%

    No Known Activations