© 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. 34-GEMMASCOPE-RES-131K
    7. 102764
    Prev
    Next
    INDEX
    Explanations

    Tev, Teo, Teb names

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

    The neuron activates on tokens that are purely numeric or contain digit sequences (e.g. years, IDs, version numbers).

    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
     Pictures
    -0.79
     frase
    -0.78
     Expect
    -0.78
     selfishness
    -0.77
    дев
    -0.74
    ورج
    -0.73
    Pictures
    -0.72
    imuth
    -0.72
    uchungen
    -0.72
    Expect
    -0.70
    POSITIVE LOGITS
     Te
    0.85
    が良い
    0.84
     Teg
    0.80
     $($
    0.79
    supplied
    0.77
    nical
    0.76
    displayed
    0.75
    Naissance
    0.74
    equip
    0.73
     egyéb
    0.73
    Activations Density 0.046%

    No Known Activations