© 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. 2709
    Prev
    Next
    INDEX
    Explanations

    formed bands or groups

    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
     ۲۰۱
    -1.16
    mphony
    -1.09
     last
    -1.07
    ariatric
    -1.03
    ánea
    -1.01
     förra
    -1.01
    vieran
    -0.97
    ỡng
    -0.96
     ২০১
    -0.95
     глоба
    -0.95
    POSITIVE LOGITS
     chambre
    1.05
     nightlife
    0.98
     тогда
    0.97
    kontak
    0.97
     прия
    0.95
    .¹
    0.95
     fucked
    0.94
     fuck
    0.94
     roommates
    0.93
     sacerdotes
    0.93
    Activations Density 0.076%

    No Known Activations