© 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. 68751
    Prev
    Next
    INDEX
    Explanations

    sudden arrival or appearance

    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
    oggi
    -1.25
     currently
    -1.07
     that
    -1.05
     nawet
    -1.02
    même
    -0.99
    ⚑
    -0.96
     Trouver
    -0.96
     кухне
    -0.96
     especialidad
    -0.94
     today
    -0.92
    POSITIVE LOGITS
     suddenly
    1.25
     came
    1.13
     plötzlich
    1.09
     вместо
    1.05
     emerge
    1.04
     announcement
    1.02
     megjelen
    1.01
     emerges
    1.00
     incoming
    0.97
     appears
    0.96
    Activations Density 0.023%

    No Known Activations