© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48980
    Prev
    Next
    INDEX
    Explanations

    rocky mountain geographic features

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

    The neuron detects proper‐name references to mountains (e.g. “Rocky Mountain,” “White Mountain,” “Great Smoky Mountains,” etc.).

    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
    shape
    -0.82
    kehrt
    -0.78
    hape
    -0.76
     Paulus
    -0.73
    OrWhiteSpace
    -0.72
     SHAPE
    -0.69
     Ery
    -0.68
    ⟺
    -0.68
    baly
    -0.65
    richTextPanel
    -0.65
    POSITIVE LOGITS
     Mieter
    0.75
     Twisted
    0.72
     Feels
    0.69
     toilet
    0.68
     poetic
    0.68
     lacks
    0.68
    掘
    0.68
     school
    0.68
     feels
    0.67
     још
    0.67
    Activations Density 0.033%

    No Known Activations