© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15232
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

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

    The neuron strongly activates on numeric tokens—especially decimal‐formatted numbers (e.g. page/volume citations).

    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
     emballage
    -1.52
     choisis
    -1.48
     multicolore
    -1.48
    nargs
    -1.47
     sû
    -1.44
    眎
    -1.43
     Visite
    -1.40
     maniere
    -1.40
     papiers
    -1.38
     palme
    -1.38
    POSITIVE LOGITS
     and
    2.14
     verschiedenen
    1.45
     or
    1.41
    结语
    1.38
     both
    1.34
    してます
    1.32
     flere
    1.27
     July
    1.27
     및
    1.27
     And
    1.26
    Activations Density 0.001%

    No Known Activations