© 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. 50327
    Prev
    Next
    INDEX
    Explanations

    detecting software and hardware environments

    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
    simus
    -0.86
     Valerie
    -0.86
    ammlung
    -0.82
    Aktualisiert
    -0.81
     coorden
    -0.79
     nhóm
    -0.76
    Valerie
    -0.76
    тина
    -0.73
     glos
    -0.73
    Compare
    -0.73
    POSITIVE LOGITS
     detection
    3.56
     detect
    3.41
     detected
    3.33
    detect
    3.20
     Detect
    3.14
     detecting
    3.02
    Detect
    2.97
    detected
    2.84
     detects
    2.84
    detection
    2.84
    Activations Density 0.161%

    No Known Activations