© 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. 30112
    Prev
    Next
    INDEX
    Explanations

    interval timing

    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
    Negative Logits
     exceedingly
    -1.16
     variedade
    -1.11
    ’,
    -1.05
     unending
    -1.03
    כום
    -1.03
    aceite
    -1.02
     quintessential
    -1.02
     colossal
    -1.01
    selben
    -0.99
     verborgen
    -0.98
    POSITIVE LOGITS
     between
    1.27
    lic
    1.23
     For
    1.20
    💕
    1.11
     между
    1.10
    典型
    1.09
    ностью
    1.05
     begins
    1.05
    ometer
    1.04
    timer
    1.03
    Activations Density 0.008%

    No Known Activations