© 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. 22-GEMMASCOPE-RES-131K
    7. 36206
    Prev
    Next
    INDEX
    Explanations

    Copyright notices or technical details

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

    The neuron is responsive to standalone numeric tokens (digit sequences).

    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
     both
    -1.78
     this
    -1.61
     most
    -1.55
     if
    -1.55
     with
    -1.41
     not
    -1.41
     in
    -1.39
     by
    -1.38
     specific
    -1.34
     any
    -1.33
    POSITIVE LOGITS
     Auffassung
    1.29
     .......
    1.16
     .........
    1.12
     tumultuous
    1.12
    Instead
    1.12
     quintessential
    1.11
    irée
    1.10
     dieselben
    1.09
    髌
    1.08
    뚠
    1.07
    Activations Density 0.001%

    No Known Activations