© 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. 60341
    Prev
    Next
    INDEX
    Explanations

    oft- heard, cited, rumored

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

    This neuron responds to the archaic/abbreviated adverb “oft” (and its variants, e.g. “Oft,” “oftentimes”).

    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
    ם
    -2.36
    沇
    -2.30
    )’
    -2.30
    嫒
    -2.25
    ſam
    -2.13
    珰
    -2.11
    驀
    -2.09
    狆
    -2.02
    柃
    -2.02
    原始内容存档
    -2.00
    POSITIVE LOGITS
    )
    2.72
    是
    2.61
     modernes
    2.52
    不管是
    2.50
     scorn
    2.50
     stalwart
    2.50
     we
    2.47
     pembun
    2.44
     brooding
    2.38
    ?"
    2.36
    Activations Density 0.004%

    No Known Activations