© 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. 79417
    Prev
    Next
    INDEX
    Explanations

    We all

    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
     your
    -0.93
     другими
    -0.92
    ;%
    -0.87
     will
    -0.86
    Fitment
    -0.85
     myös
    -0.85
    cliente
    -0.85
    <td>
    -0.84
     bude
    -0.83
    rillation
    -0.83
    POSITIVE LOGITS
     often
    1.80
     humans
    1.73
     tend
    1.46
    Humans
    1.41
     all
    1.38
     souvent
    1.26
     sometimes
    1.23
     Humans
    1.20
    humans
    1.18
    often
    1.16
    Activations Density 0.045%

    No Known Activations