© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116291
    Prev
    Next
    INDEX
    Explanations

    karma and awards

    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
     lentil
    -0.82
    亰
    -0.81
    المشاركات
    -0.78
     Pistons
    -0.77
     Chlor
    -0.73
     Yates
    -0.73
     {%
    -0.73
     PRINCIPAL
    -0.72
     عش
    -0.71
     Pb
    -0.71
    POSITIVE LOGITS
     flair
    1.80
     Flair
    1.33
    fla
    1.15
     fla
    1.09
     praw
    0.98
     award
    0.96
    Fla
    0.92
     removal
    0.89
     awards
    0.88
     flare
    0.88
    Activations Density 0.043%

    No Known Activations