© 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. 34-GEMMASCOPE-RES-131K
    4. 90256
    Prev
    Next
    INDEX
    Explanations

    citations and references

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

    The neuron activates on standalone numeric tokens (i.e. numbers and 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_34/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
     (!__
    -0.98
    cives
    -0.94
    另一
    -0.90
     nevertheless
    -0.86
    ylvanian
    -0.84
    andalf
    -0.82
     requirements
    -0.82
     sufficiently
    -0.82
     and
    -0.81
     that
    -0.81
    POSITIVE LOGITS
     (
    1.30
     scolaires
    0.94
    schuhe
    0.94
    (
    0.92
     Aragon
    0.88
     fintech
    0.87
     extérieures
    0.87
    promise
    0.87
    дьми
    0.86
    SEASON
    0.85
    Activations Density 0.011%

    No Known Activations