© 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. 57183
    Prev
    Next
    INDEX
    Explanations

    conventional versus specific terms

    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
     atypical
    -1.07
    特殊的
    -1.01
     unconventional
    -0.93
    alternative
    -0.90
     esports
    -0.89
     zelen
    -0.89
    专门
    -0.89
     lecciones
    -0.87
     promete
    -0.86
     aviation
    -0.84
    POSITIVE LOGITS
     mainstream
    1.23
     heterosexual
    1.05
     conventional
    1.00
     IgG
    0.94
     standard
    0.94
     regular
    0.94
    普通
    0.92
    MAIN
    0.92
     réguli
    0.91
     English
    0.90
    Activations Density 0.612%

    No Known Activations