© 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. 62370
    Prev
    Next
    INDEX
    Explanations

    state and admission

    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
     vencer
    -0.77
    lende
    -0.76
    aub
    -0.72
     ordinaire
    -0.70
    ⠻
    -0.68
    挑戦
    -0.67
    bonjour
    -0.67
    intura
    -0.67
    ordenadas
    -0.67
     canning
    -0.66
    POSITIVE LOGITS
     admission
    1.78
     state
    1.77
     Admission
    1.65
    admission
    1.51
    Admission
    1.50
    state
    1.48
     admitted
    1.42
     State
    1.41
     estado
    1.32
     admissions
    1.27
    Activations Density 0.023%

    No Known Activations