© 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. 79402
    Prev
    Next
    INDEX
    Explanations

    restore and reign

    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
     on
    -0.91
     in
    -0.85
     or
    -0.81
     with
    -0.81
     by
    -0.80
     more
    -0.79
     those
    -0.79
     during
    -0.79
    蔬
    -0.79
     at
    -0.77
    POSITIVE LOGITS
    restore
    1.07
    Restore
    1.07
     Restore
    0.92
     restore
    0.90
    ඌ
    0.86
    𝓕
    0.85
    禳
    0.84
    ɇ
    0.84
    ඍ
    0.84
    CSRF
    0.83
    Activations Density 0.001%

    No Known Activations