© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13949
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    The neuron fires strongly on isolated number tokens (digits and small numeric values) in code/math contexts.

    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
     ones
    -0.95
    𝟭
    -0.94
    فو
    -0.93
    weiter
    -0.93
     acostumb
    -0.93
    為に
    -0.92
    cfd
    -0.89
    噛
    -0.89
    COLL
    -0.89
    footnotes
    -0.89
    POSITIVE LOGITS
    がありますが
    1.25
    調味料
    1.19
    最近は
    1.13
    これは
    1.12
    そして
    1.10
    などなど
    1.07
    があり
    1.06
    Уже
    1.05
    eamiento
    1.05
     whereas
    1.02
    Activations Density 0.015%

    No Known Activations