© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66088
    Prev
    Next
    INDEX
    Explanations

    stamp, card, sentiment, image, stencils

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

    The neuron fires strongly on mentions of handmade greeting cards (e.g. “card,” “made,” “sentiment”) in crafting-blog posts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    :
    -1.62
    に行きました
    -1.59
     after
    -1.52
    に行ってきました
    -1.48
     речо
    -1.43
    了一声
    -1.41
     long
    -1.39
    ַּ
    -1.37
     mengangg
    -1.34
    ;
    -1.30
    POSITIVE LOGITS
     utiliser
    1.66
    隂
    1.55
     legato
    1.39
     utilisant
    1.38
     rupiah
    1.36
    ofing
    1.35
    kuu
    1.31
    wijl
    1.27
    titure
    1.27
    loài
    1.25
    Activations Density 0.046%

    No Known Activations