© 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. 28358
    Prev
    Next
    INDEX
    Explanations

    code directives and attributes

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

    The neuron is sensitive to numeric tokens, i.e. sequences of digits.

    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
     from
    -1.02
    innung
    -0.90
     Kammer
    -0.90
    нам
    -0.89
     cucchia
    -0.89
     kuni
    -0.86
    ższe
    -0.86
    ила
    -0.85
     bianche
    -0.85
    ̀u
    -0.85
    POSITIVE LOGITS
     áng
    0.99
     inhalt
    0.98
     buchen
    0.97
     principais
    0.97
     cáp
    0.96
     obere
    0.95
    房地产
    0.93
     necessárias
    0.93
     Gesetze
    0.92
     čer
    0.92
    Activations Density 0.018%

    No Known Activations