© 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. 106257
    Prev
    Next
    INDEX
    Explanations

    it has taken

    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
     preocu
    -1.10
    ⎧
    -1.02
    給你
    -1.02
    に入れる
    -0.99
     centaines
    -0.97
    􏰁
    -0.97
    裆
    -0.96
    trying
    -0.95
     يمكنك
    -0.95
     proposent
    -0.91
    POSITIVE LOGITS
     gets
    1.45
     sits
    1.45
     stays
    1.42
     lives
    1.41
     become
    1.37
     remain
    1.34
     stay
    1.34
     staying
    1.33
     lived
    1.30
     serve
    1.29
    Activations Density 0.060%

    No Known Activations