© 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. 69198
    Prev
    Next
    INDEX
    Explanations

    shut down

    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
     množství
    -0.99
     alimente
    -0.97
     děti
    -0.97
     otorga
    -0.96
    せっかく
    -0.94
    ゆったり
    -0.94
    ಇ
    -0.93
    洗澡
    -0.93
    いよいよ
    -0.92
    platos
    -0.91
    POSITIVE LOGITS
     or
    1.23
    なのかな
    1.02
     not
    0.97
    だという
    0.97
    jamos
    0.96
     time
    0.96
     it
    0.94
    兇
    0.94
     terminée
    0.94
    átní
    0.93
    Activations Density 0.097%

    No Known Activations