© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57496
    Prev
    Next
    INDEX
    Explanations

    size and fit

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

    The neuron fires on mentions of sizing, fit, and adjustment details (e.g. clothing measurements or how large/small something is).

    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
    տ
    -0.80
    setta
    -0.80
    🥽
    -0.79
     maxY
    -0.77
     эффективности
    -0.75
    效率
    -0.74
    リエーション
    -0.73
     smoothness
    -0.73
     угол
    -0.73
     stär
    -0.72
    POSITIVE LOGITS
     oversized
    1.51
     roomy
    1.29
     oversize
    1.27
     size
    1.22
     loose
    1.20
     baggy
    1.20
     loosen
    1.10
     spacious
    1.09
     fit
    1.07
    LARGE
    1.06
    Activations Density 0.013%

    No Known Activations