© 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. 62645
    Prev
    Next
    INDEX
    Explanations

    model-based compounds

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

    The neuron fires on occurrences of the term “model” (in any casing or context).

    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
    𝘺
    -0.84
    ades
    -0.78
    ᴺ
    -0.75
    geth
    -0.73
    ㍍
    -0.72
    贪
    -0.71
    evre
    -0.71
     SOCK
    -0.71
    ī
    -0.71
     mov
    -0.70
    POSITIVE LOGITS
    |_{\
    0.79
     MCQ
    0.79
     Theorems
    0.77
     miliki
    0.77
    ailer
    0.75
     længere
    0.74
    IDENTIAL
    0.73
    AndView
    0.73
    orian
    0.73
     vengan
    0.72
    Activations Density 0.028%

    No Known Activations