© 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. 10-GEMMASCOPE-RES-131K
    7. 104825
    Prev
    Next
    INDEX
    Explanations

    'based' followed by a descriptor

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

    The neuron reliably activates on the standalone token “Based,” i.e. occurrences of “-based” in compound terms.

    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
     "
    -4.06
    ’
    -3.41
     was
    -2.97
    </h1>
    -2.92
     comprennent
    -2.64
     BOTH
    -2.53
     añadido
    -2.53
     vivent
    -2.38
    </i>
    -2.34
     réduit
    -2.33
    POSITIVE LOGITS
    𖥦
    2.64
     '-':
    2.47
    based
    2.41
    ेमाल
    2.34
    <em>
    2.34
    ي
    2.30
    You
    2.23
     upcoming
    2.22
    providedIn
    2.20
    景观
    2.20
    Activations Density 0.049%

    No Known Activations