© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78072
    Prev
    Next
    INDEX
    Explanations

    it under the terms

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

    The neuron detects GPL-style license grant phrasing (e.g. the “redistribute it and/or modify it under the terms of the GNU … License” boilerplate).

    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
     able
    -0.98
    thylamine
    -0.81
     verste
    -0.81
     ANSWERS
    -0.79
     its
    -0.78
     teclas
    -0.76
    めんな
    -0.76
    HttpHeaders
    -0.75
     imprimible
    -0.75
    metic
    -0.74
    POSITIVE LOGITS
    Self
    1.00
    continue
    0.82
     Self
    0.81
     SELF
    0.81
     self
    0.79
    ⎨
    0.79
    但是在
    0.78
    self
    0.78
     recognition
    0.77
    Skip
    0.76
    Activations Density 0.030%

    No Known Activations