© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47119
    Prev
    Next
    INDEX
    Explanations

    product specifications and details

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

    the neuron spots technical specification elements such as model or specification labels, numeric values, and their associated units.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    authors
    -1.23
     tarif
    -0.93
     elek
    -0.90
     telefonu
    -0.89
    自作
    -0.85
    whereas
    -0.85
     miniaturka
    -0.84
    Consequently
    -0.84
     akus
    -0.84
    fingers
    -0.83
    POSITIVE LOGITS
     material
    1.39
     weight
    1.33
     color
    1.11
     product
    1.09
    material
    1.07
    Size
    1.03
    Material
    1.03
    Applicable
    1.02
     suitable
    1.02
     size
    1.02
    Activations Density 0.005%

    No Known Activations