© 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. 277
    Prev
    Next
    INDEX
    Explanations

    the following conditions

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

    The neuron detects key terms from software license boilerplate, especially the “provided that the following conditions are met” clause.

    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
    ühnen
    -0.77
    DEPTH
    -0.77
    iddle
    -0.73
     concealed
    -0.73
     conceal
    -0.71
    ását
    -0.71
     заинтере
    -0.70
     replacement
    -0.70
     replace
    -0.69
     depth
    -0.69
    POSITIVE LOGITS
    mush
    0.71
     accompagner
    0.66
     Natur
    0.64
    แป
    0.63
     Control
    0.63
    撹
    0.62
     Biosciences
    0.61
     SCORE
    0.61
    приятий
    0.60
    Abd
    0.59
    Activations Density 0.058%

    No Known Activations