© 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. 30234
    Prev
    Next
    INDEX
    Explanations

    instantiateViewController withIdentifier UIView

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ланд
    -1.00
    cao
    -0.92
    бер
    -0.90
     what
    -0.88
    VisualStudio
    -0.88
     harap
    -0.87
     информация
    -0.86
    wikipedia
    -0.86
     dataGridView
    -0.85
    rache
    -0.83
    POSITIVE LOGITS
    今週
    0.93
    今回も
    0.90
    Utility
    0.90
     szary
    0.90
     caméra
    0.88
     multe
    0.86
     obj
    0.86
    alimentos
    0.84
    ネタバレ
    0.84
    trimmed
    0.84
    Activations Density 0.027%

    No Known Activations