© 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. 34-GEMMASCOPE-RES-131K
    7. 65273
    Prev
    Next
    INDEX
    Explanations

    birth and death dates

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

    The neuron strongly activates on numeric tokens (digits and number-related punctuation), i.e. it detects when the text is expressing 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
     Juliette
    -0.84
     INGRED
    -0.82
     comprise
    -0.82
     PHILL
    -0.79
     Then
    -0.77
    ètres
    -0.76
     شدند
    -0.75
    ʎ
    -0.75
     verpflichtet
    -0.75
     FRUIT
    -0.73
    POSITIVE LOGITS
     predeceased
    0.93
     leaving
    0.93
     passing
    0.85
    dodge
    0.82
     dodge
    0.82
    通過
    0.82
     pass
    0.81
     leave
    0.80
    excellents
    0.80
     loved
    0.79
    Activations Density 0.001%

    No Known Activations