© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58760
    Prev
    Next
    INDEX
    Explanations

    saving game 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
    raa
    -0.85
    bree
    -0.73
     redshift
    -0.71
     categoria
    -0.70
    滞
    -0.69
    seeking
    -0.69
    混乱
    -0.68
    🔼
    -0.68
    滯
    -0.68
    österreich
    -0.67
    POSITIVE LOGITS
     save
    4.44
    save
    3.69
     saves
    3.56
     Save
    3.39
    Save
    3.33
     saved
    3.33
     SAVE
    2.97
     saving
    2.88
    SAVE
    2.84
     Saves
    2.66
    Activations Density 0.026%

    No Known Activations