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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83401
    Prev
    Next
    INDEX
    Explanations

    reports and findings

    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
    chedule
    -0.93
     Sus
    -0.92
    ੨
    -0.91
    ׇ
    -0.91
    prova
    -0.90
     esetén
    -0.89
    ❓
    -0.88
    Obituary
    -0.87
    ῴ
    -0.85
     kialak
    -0.84
    POSITIVE LOGITS
     findings
    2.86
     conclusions
    2.20
     report
    2.20
    Findings
    1.98
     Findings
    1.83
     released
    1.72
     research
    1.71
     study
    1.70
     commissioned
    1.69
     FINDINGS
    1.62
    Activations Density 0.077%

    No Known Activations