© 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. 56109
    Prev
    Next
    INDEX
    Explanations

    Nac, Nach, Zac, zač

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

    The neuron activates on tokens containing the letter sequence “nac” (in any casing).

    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
     carica
    -0.78
    voyance
    -0.78
    nosotros
    -0.77
     régiment
    -0.73
     bambina
    -0.73
     Molecule
    -0.71
    caux
    -0.71
    plit
    -0.70
    inare
    -0.69
     handleChange
    -0.69
    POSITIVE LOGITS
     αρχ
    0.86
     Nac
    0.80
    VAO
    0.79
    গ্র
    0.74
    いじ
    0.70
    ünk
    0.69
    INITIAL
    0.68
    keyframes
    0.67
     Beal
    0.66
     περ
    0.66
    Activations Density 0.023%

    No Known Activations