© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73421
    Prev
    Next
    INDEX
    Explanations

    provided that conditions

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

    The neuron detects boilerplate licence‐grant or permission clauses (e.g. “provided,” “permitted,” “are,” “modification”) in source‐code headers.

    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
     Curriculum
    -0.89
    স্
    -0.75
     Deletion
    -0.75
     Lad
    -0.74
    ieds
    -0.72
     почина
    -0.71
    ريف
    -0.70
     落
    -0.70
    ässer
    -0.69
    Archiv
    -0.69
    POSITIVE LOGITS
    transitions
    0.68
    parency
    0.68
    forty
    0.65
     一人
    0.64
     ボディ
    0.64
     ceremonia
    0.64
    psychiat
    0.63
     clásico
    0.63
     preacher
    0.62
    olesome
    0.62
    Activations Density 0.056%

    No Known Activations