© 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. 22-GEMMASCOPE-RES-131K
    7. 70798
    Prev
    Next
    INDEX
    Explanations

    conditions for alerts

    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_22/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
    还能
    -0.87
    approximately
    -0.86
    TEMA
    -0.86
    trying
    -0.84
    拼命
    -0.84
    without
    -0.83
    ajo
    -0.83
    xtures
    -0.82
     caráter
    -0.80
    mité
    -0.80
    POSITIVE LOGITS
     thresholds
    1.49
     threshold
    1.47
     criteria
    1.30
    threshold
    1.27
    Threshold
    1.18
     Threshold
    1.13
     monitoring
    1.10
    THRESHOLD
    1.08
     conditions
    1.06
     criterion
    1.05
    Activations Density 0.130%

    No Known Activations