© 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. 48911
    Prev
    Next
    INDEX
    Explanations

    words starting with Zo

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

    This neuron fires on tokens containing the letter sequence “zo,” e.g. parts of names or words like Zoho, Zoloft, Zorn, Zomba, zorba, 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
     jenen
    -0.77
    itchfield
    -0.77
    usin
    -0.75
     おもちゃ
    -0.75
    swar
    -0.73
    Penta
    -0.73
     опла
    -0.72
     Autop
    -0.72
     statement
    -0.71
    glacial
    -0.71
    POSITIVE LOGITS
     Caso
    0.80
     altrimenti
    0.72
    bele
    0.71
    itet
    0.71
    signs
    0.70
    removeAttr
    0.69
     Neale
    0.68
    ӧ
    0.68
    logOut
    0.66
     otherwise
    0.66
    Activations Density 0.027%

    No Known Activations