© 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. 10-GEMMASCOPE-RES-131K
    7. 111546
    Prev
    Next
    INDEX
    Explanations

    names and places with ford

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

    The neuron activates on occurrences of the substring “ford” in tokens (e.g. names like Wolford, Crockford, Fulford, Hartford).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     "
    -2.97
    ological
    -2.72
    ization
    -2.52
     所以
    -2.41
    躂
    -2.38
    くちゃ
    -2.34
     colocando
    -2.27
     queridos
    -2.17
    葑
    -2.11
     abiertas
    -2.05
    POSITIVE LOGITS
    Y
    2.78
    逦
    2.63
    meteries
    2.61
    洐
    2.55
    ford
    2.52
    媄
    2.42
    .“
    2.30
    $
    2.27
    <td>
    2.20
    }}{\
    2.20
    Activations Density 0.007%

    No Known Activations