© 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. 60788
    Prev
    Next
    INDEX
    Explanations

    triggering events or states

    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
    gı
    -0.88
    SqlConnection
    -0.80
     prohibiting
    -0.74
    afterEach
    -0.74
    psy
    -0.74
    зани
    -0.73
    suited
    -0.72
    enumii
    -0.71
     divertir
    -0.71
    ukun
    -0.71
    POSITIVE LOGITS
     trigger
    5.13
     triggering
    4.75
     triggers
    4.75
    trigger
    4.44
     Trigger
    4.06
    Trigger
    4.00
     triggered
    3.92
     Triggers
    3.83
    triggers
    3.55
    Triggers
    3.44
    Activations Density 0.509%

    No Known Activations