© 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. 34-GEMMASCOPE-RES-131K
    7. 47340
    Prev
    Next
    INDEX
    Explanations

    concepts and theories

    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
    PX
    -0.95
     ralph
    -0.90
    ppling
    -0.85
     opel
    -0.85
     philosop
    -0.84
    ilets
    -0.83
    ♥
    -0.83
     тобой
    -0.81
     noodle
    -0.81
     peugeot
    -0.81
    POSITIVE LOGITS
     reception
    1.07
     Reception
    0.98
     config
    0.98
     oferty
    0.92
     elites
    0.90
    ড
    0.88
     methodical
    0.87
     versátil
    0.87
    Chances
    0.86
     elated
    0.84
    Activations Density 0.055%

    No Known Activations