© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128172
    Prev
    Next
    INDEX
    Explanations

    ast related words

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

    This neuron responds to the letter sequence “ast” (e.g. at the start of words like “Astros,” “astaxanthin,” or “astound”).

    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
    呖
    -3.23
    ︲
    -2.94
    ه
    -2.67
    </td>
    -2.59
    ⚋
    -2.58
     médaille
    -2.55
    蹀
    -2.53
     frontière
    -2.50
    м
    -2.48
     totalité
    -2.41
    POSITIVE LOGITS
    {
    4.66
    </strong>
    2.89
     formidable
    2.72
     Bereichen
    2.50
    鬭
    2.48
    ᡴ
    2.47
    各种
    2.42
            
    2.38
    ковой
    2.36
     Mitteln
    2.28
    Activations Density 0.003%

    No Known Activations