© 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. 78434
    Prev
    Next
    INDEX
    Explanations

    reports, findings, trends, tables, results

    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
     Listed
    -0.85
     if
    -0.84
    Recorded
    -0.82
    startGame
    -0.82
     during
    -0.82
     after
    -0.81
    sibilities
    -0.81
     lista
    -0.79
     as
    -0.78
     gedurende
    -0.78
    POSITIVE LOGITS
     trends
    1.55
     tables
    1.30
    trends
    1.30
     findings
    1.25
     summary
    1.22
     results
    1.22
     Findings
    1.20
    Tables
    1.19
     TRENDS
    1.15
     Trends
    1.13
    Activations Density 0.071%

    No Known Activations