© 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. 57637
    Prev
    Next
    INDEX
    Explanations

    branches and sects

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     rasp
    -0.85
    シブル
    -0.82
     profit
    -0.82
    马来
    -0.79
     offer
    -0.79
     convenient
    -0.78
     offers
    -0.77
     Coulter
    -0.76
    キッズ
    -0.74
     profits
    -0.73
    POSITIVE LOGITS
     branch
    1.45
    派
    1.16
     sect
    1.16
    branch
    1.13
     branches
    1.09
     sects
    1.09
     aliran
    1.08
     followers
    1.07
    分支
    1.07
    Branch
    1.05
    Activations Density 0.047%

    No Known Activations