© 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. 100835
    Prev
    Next
    INDEX
    Explanations

    experience with difficulties

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

    The neuron activates on numeric tokens (especially measurements and counts, including decimal numbers).

    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
     of
    -1.75
    of
    -1.75
    l
    -1.63
    Table
    -1.63
     本
    -1.57
    鲮
    -1.55
    ANCO
    -1.55
    
    -1.52
     و
    -1.52
     Kenntnis
    -1.50
    POSITIVE LOGITS
     столько
    1.73
    ︓
    1.69
     közül
    1.63
    </td>
    1.62
    "،
    1.60
    躂
    1.59
    品種
    1.59
    
    1.59
     között
    1.58
    ཫ
    1.57
    Activations Density 0.026%

    No Known Activations