© 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. 34-GEMMASCOPE-RES-131K
    7. 75465
    Prev
    Next
    INDEX
    Explanations

    preceding ones

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

    The neuron strongly activates on adjectives and adverbs that mark size or position in a sequence (e.g. initial, middle, last, smaller, biggest).

    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
    いろいろな
    -1.09
    色んな
    -1.01
    いろんな
    -0.99
    筈
    -0.97
     Эти
    -0.96
    雰囲気が
    -0.94
     essas
    -0.94
     diversos
    -0.93
    ること
    -0.93
     a
    -0.92
    POSITIVE LOGITS
     ones
    9.88
    Ones
    5.06
     Ones
    4.66
    ones
    4.44
     quelli
    4.25
     those
    3.44
    ONES
    3.03
    のもの
    2.98
     celles
    2.83
     ceux
    2.73
    Activations Density 0.364%

    No Known Activations