© 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. 47951
    Prev
    Next
    INDEX
    Explanations

    proof and proving

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

    The neuron fires on occurrences of the root “prov-” (e.g. “prove,” “proving,” “proves”) in text.

    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
     ``
    -2.30
     '
    -2.30
     ''
    -2.17
     \"
    -2.16
    
    -1.90
    ]
    -1.79
     entonces
    -1.75
    迓
    -1.73
     ""
    -1.70
     ?
    -1.69
    POSITIVE LOGITS
    It
    2.09
     ofere
    2.03
    〜〜
    1.98
    綃
    1.94
     dificuldades
    1.94
     estabele
    1.92
     安心
    1.89
    寕
    1.88
    <td>
    1.87
    殞
    1.86
    Activations Density 0.046%

    No Known Activations