© 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. 94249
    Prev
    Next
    INDEX
    Explanations

    set apart

    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
     situés
    -0.83
    Haber
    -0.78
     élas
    -0.77
    Johns
    -0.77
     torebka
    -0.77
    驻
    -0.77
    MITTED
    -0.75
     différentes
    -0.75
     graphiques
    -0.75
     extérieurs
    -0.74
    POSITIVE LOGITS
     ablaze
    1.59
     aside
    1.35
     for
    1.20
     parameters
    1.19
     alight
    1.11
     traps
    1.10
     tone
    1.09
     adrift
    1.07
     apart
    1.01
     forth
    0.96
    Activations Density 0.028%

    No Known Activations