© 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. 66664
    Prev
    Next
    INDEX
    Explanations

    place names like Ponte Vedra

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

    The neuron flags Spanish verb forms that carry an enclitic pronoun (e.g. infinitives or imperatives ending in “–arse,” gerunds like “–ándome,” imperatives like “–icate,” etc.).

    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
    ſelves
    -2.91
    骘
    -2.63
     you
    -2.08
     We
    -2.06
    ным
    -2.05
     or
    -1.98
     sumber
    -1.95
    }]
    -1.92
     "
    -1.91
     ή
    -1.88
    POSITIVE LOGITS
    
    2.50
    衚
    2.44
     باسلام
    2.38
    놋
    2.36
    𖣘
    2.34
    ครื่อง
    2.25
    饃
    2.22
    
    2.19
    
    2.17
    逦
    2.16
    Activations Density 0.002%

    No Known Activations