© 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. 10-GEMMASCOPE-RES-131K
    7. 98906
    Prev
    Next
    INDEX
    Explanations

    press releases and political representatives

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

    The neuron activates on the LaTeX “\propto” proportional‐to command.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     "-
    -2.81
     '-
    -2.64
     was
    -2.50
     что
    -2.30
     has
    -2.25
    ]
    -2.23
     следующие
    -2.23
     =
    -2.22
     ['./
    -2.20
    看到的
    -2.20
    POSITIVE LOGITS
    er
    2.70
    汌
    2.66
     合集
    2.41
     nahil
    2.25
    selben
    2.23
     剧照
    2.22
     lainnya
    2.22
     anún
    2.19
    桖
    2.19
     vergeten
    2.16
    Activations Density 0.001%

    No Known Activations