© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3285
    Prev
    Next
    INDEX
    Explanations

    external website profiles

    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
     Pristupljeno
    -0.93
     such
    -0.88
    RelativeTo
    -0.85
     vermek
    -0.77
    ãn
    -0.76
     tender
    -0.75
     пора
    -0.74
     weight
    -0.74
    וך
    -0.74
     depend
    -0.73
    POSITIVE LOGITS
    页面存档备份
    1.90
    enlace
    1.17
    archive
    1.13
    Memento
    1.09
     archive
    1.09
    Архівовано
    1.04
     Archived
    1.02
     Archive
    1.00
    Archived
    0.99
    Archive
    0.97
    Activations Density 0.011%

    No Known Activations