© 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. 64783
    Prev
    Next
    INDEX
    Explanations

    it doesn't matter

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

    The neuron fires on the isolated token “t” (the single-character t syllable that often appears in splits of words like don’t, it’s, isn’t, etc.).

    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
     Teig
    -0.90
    inent
    -0.90
    voie
    -0.89
     можем
    -0.86
    ìn
    -0.86
     pasir
    -0.85
     voulais
    -0.85
     pakan
    -0.85
    lighed
    -0.82
     infek
    -0.82
    POSITIVE LOGITS
     matter
    1.55
     help
    1.32
     hurt
    1.29
     compare
    1.12
     even
    1.09
     really
    1.06
     seem
    1.05
     Compare
    1.05
     совсем
    1.04
     mattered
    1.02
    Activations Density 0.047%

    No Known Activations