© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80942
    Prev
    Next
    INDEX
    Explanations

    sticky notes or navigation

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

    The neuron flags technical/specification or instructional language—phrases that give sizes, dimensions, product details, methods, or calls to action.

    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
    iedene
    -0.82
     wheelchairs
    -0.80
    anterie
    -0.77
    INTEL
    -0.76
     Gibbons
    -0.73
     گردشگری
    -0.72
    IGraphics
    -0.72
     Martens
    -0.71
    dius
    -0.70
    pees
    -0.70
    POSITIVE LOGITS
     sticky
    1.24
     notes
    1.20
     Notes
    1.17
    notes
    1.07
    Sticky
    1.05
     note
    1.05
    index
    1.02
     index
    0.96
     Sticky
    0.94
    Notes
    0.93
    Activations Density 0.009%

    No Known Activations