© 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. 62886
    Prev
    Next
    INDEX
    Explanations

    // or # comments

    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
     például
    -2.08
     notamment
    -1.84
     réun
    -1.76
     supuestamente
    -1.75
     légitime
    -1.73
     ziemlich
    -1.70
    excellents
    -1.70
     This
    -1.70
     moviliz
    -1.69
     relativement
    -1.68
    POSITIVE LOGITS
     since
    1.84
     after
    1.80
     if
    1.73
     but
    1.71
     although
    1.70
     there
    1.63
     because
    1.62
     could
    1.61
     when
    1.57
     see
    1.57
    Activations Density 0.130%

    No Known Activations