© 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. 60907
    Prev
    Next
    INDEX
    Explanations

    it either

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

    The neuron strongly activates on software‐license boilerplate text (e.g. GPL redistribution/modification wording and related terms).

    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
    owned
    -0.77
     owned
    -0.76
    Owned
    -0.75
    λικ
    -0.73
    _->
    -0.71
    }))
    -0.70
     Гі
    -0.70
    thme
    -0.69
     Owned
    -0.69
    infer
    -0.69
    POSITIVE LOGITS
     Taurus
    0.83
     obtu
    0.68
     perm
    0.65
     хотела
    0.63
    elu
    0.63
    ."*
    0.63
     проще
    0.63
    浿
    0.62
    と一緒に
    0.62
     elas
    0.62
    Activations Density 0.054%

    No Known Activations