© 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. 34-GEMMASCOPE-RES-131K
    7. 1629
    Prev
    Next
    INDEX
    Explanations

    neither, none, nothing

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

    The neuron fires on tokens of “find”–type verbs (e.g. achar/encontrar in Portuguese) in first‐person contexts (e.g. “achei,” “encontrei”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     segala
    -0.99
     biraz
    -0.97
     herkes
    -0.94
     også
    -0.92
     rất
    -0.91
    だけでなく
    -0.89
     piuttosto
    -0.89
     症
    -0.89
     också
    -0.88
    jsk
    -0.85
    POSITIVE LOGITS
     neither
    4.44
    neither
    3.61
     none
    3.38
     nothing
    3.34
    Neither
    3.23
     هیچ
    3.22
     Neither
    3.08
     ninguna
    3.03
     żad
    3.03
     ningún
    2.88
    Activations Density 0.028%

    No Known Activations