© 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. 47402
    Prev
    Next
    INDEX
    Explanations

    code using statements

    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
     only
    -1.27
     any
    -1.14
     more
    -1.05
     doing
    -0.98
     Only
    -0.98
     hacer
    -0.97
     supposedly
    -0.94
     Creating
    -0.93
     Knowing
    -0.92
     markedly
    -0.92
    POSITIVE LOGITS
    primarily
    1.06
    ολ
    1.02
     ESPEC
    1.00
     principalmente
    0.97
     DOUBLE
    0.97
    especially
    0.92
     ABSOL
    0.92
    mainly
    0.91
     definida
    0.91
     opportun
    0.89
    Activations Density 0.005%

    No Known Activations