© 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. 45239
    Prev
    Next
    INDEX
    Explanations

    veins, margins, and apex

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

    descriptions of physical features of plants, animals, or insects, particularly their colors, shapes, and sizes in taxonomy entries.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on numeric measurements and quantitative descriptions (e.g. counts, lengths, dimensions) in morphological or technical details.

    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
    facade
    -0.76
     antropo
    -0.71
     Fant
    -0.70
    ۫
    -0.70
    Cere
    -0.70
     Veränder
    -0.70
     смер
    -0.69
    appel
    -0.69
     Pemain
    -0.69
     peregr
    -0.68
    POSITIVE LOGITS
     veins
    1.70
     vein
    1.48
     Vein
    1.33
    vein
    1.27
     ven
    1.12
     Margin
    1.05
     margin
    0.95
    Ve
    0.94
     Ve
    0.93
     margins
    0.93
    Activations Density 0.021%

    No Known Activations