© 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. 65834
    Prev
    Next
    INDEX
    Explanations

    Porta, portafilter, portacaval, reciprocating

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

    The neuron is strongly activated by occurrences of the substring “porta.”

    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
     frühen
    -3.00
     convir
    -2.72
     feinen
    -2.61
     berühmten
    -2.52
    ↵
    -2.48
     dunklen
    -2.47
     späteren
    -2.45
     kleinen
    -2.42
     verstor
    -2.42
     üblichen
    -2.39
    POSITIVE LOGITS
    
    2.66
    饜
    2.63
    was
    2.59
    providedIn
    2.59
    媖
    2.58
    ++]=
    2.53
    嗵
    2.48
     quali
    2.45
    ’,
    2.44
    isers
    2.42
    Activations Density 0.012%

    No Known Activations