© 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. 56869
    Prev
    Next
    INDEX
    Explanations

    context

    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
    CV
    -0.80
     specimen
    -0.75
    стай
    -0.73
    cranial
    -0.72
     rash
    -0.71
    carne
    -0.71
     canon
    -0.68
    qar
    -0.67
     столе
    -0.67
     lady
    -0.67
    POSITIVE LOGITS
     context
    3.66
     Context
    2.86
     contexts
    2.77
     ctx
    2.72
    Context
    2.66
     контек
    2.61
    context
    2.59
    CONTEXT
    2.56
    ctx
    2.47
    getContext
    2.45
    Activations Density 0.036%

    No Known Activations