© 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. 68910
    Prev
    Next
    INDEX
    Explanations

    connecting different items

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

    The neuron strongly activates on numeric tokens (e.g. measurement-style numbers) wherever they appear.

    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
    ícias
    -1.30
    ख़
    -1.22
     demografica
    -1.16
    itisation
    -1.14
    tlement
    -1.14
    随即
    -1.13
    ༑
    -1.13
    phere
    -1.13
     iedereen
    -1.12
    䜣
    -1.11
    POSITIVE LOGITS
     other
    1.64
    autres
    1.15
     otras
    1.10
     diğer
    1.05
     more
    1.04
     various
    1.04
     bereits
    1.03
     an
    1.02
     increasing
    1.02
     سایر
    1.01
    Activations Density 0.157%

    No Known Activations