© 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. 23503
    Prev
    Next
    INDEX
    Explanations

    provided with software

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

    The neuron strongly activates on boilerplate license terms about materials provided with a distribution.

    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
     propiedad
    -0.75
    纳
    -0.70
    μιουργ
    -0.69
     nip
    -0.68
    FOOT
    -0.66
    Foot
    -0.65
    الصفحه
    -0.65
     chl
    -0.64
    Пре
    -0.64
    納
    -0.64
    POSITIVE LOGITS
    Patty
    0.68
    LEARN
    0.67
    isma
    0.67
    oglio
    0.67
    tvr
    0.66
     浅
    0.65
     столько
    0.65
     asser
    0.65
     Uma
    0.65
     ума
    0.64
    Activations Density 0.084%

    No Known Activations