© 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. 102390
    Prev
    Next
    INDEX
    Explanations

    skiing powder

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

    The neuron fires on the prominent, all-caps or title-case tokens used in marketing‐style headings or slogans.

    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
     slalom
    -0.82
     campsites
    -0.81
    anganese
    -0.81
    gbar
    -0.77
    xbf
    -0.77
     Pune
    -0.77
    mble
    -0.76
     ბ
    -0.73
     Golf
    -0.73
    ák
    -0.72
    POSITIVE LOGITS
     powder
    1.60
    Powder
    1.34
     Powder
    1.34
    powder
    1.30
     powdery
    0.91
    粉
    0.88
    VARD
    0.81
     helicopter
    0.81
    Territory
    0.81
     tives
    0.80
    Activations Density 0.018%

    No Known Activations