© 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. 54044
    Prev
    Next
    INDEX
    Explanations

    free of charge

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

    The neuron activates on the boilerplate license‐grant phrase “free of charge,” i.e. text granting free usage permission.

    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
    ppchen
    -0.73
    ㎢
    -0.73
    etta
    -0.69
    MODER
    -0.68
    rinhos
    -0.68
     Thiết
    -0.67
     ipod
    -0.66
     Doncaster
    -0.66
     $('#
    -0.66
     todays
    -0.66
    POSITIVE LOGITS
     Kane
    0.78
    JvmStatic
    0.75
    oyan
    0.73
     Integrity
    0.70
     paseo
    0.69
    Kane
    0.69
    homogeneous
    0.69
    UATION
    0.68
    Think
    0.68
    Anchor
    0.68
    Activations Density 0.026%

    No Known Activations