© 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. 107509
    Prev
    Next
    INDEX
    Explanations

    required by

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

    The neuron strongly activates on the word “required” (as in “Unless required by applicable law…”), effectively detecting that specific term in Apache-style 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
     JAK
    -0.74
    Уда
    -0.69
     GAB
    -0.68
     hrá
    -0.67
     CAP
    -0.66
     Gazette
    -0.66
     Savo
    -0.65
     CAG
    -0.64
    Джере
    -0.63
     SCN
    -0.63
    POSITIVE LOGITS
     ζω
    0.79
     trails
    0.70
     deterministic
    0.69
    clf
    0.64
    serie
    0.64
     słowa
    0.64
    cido
    0.63
    licht
    0.63
     BEACH
    0.63
    знес
    0.62
    Activations Density 0.072%

    No Known Activations