© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57844
    Prev
    Next
    INDEX
    Explanations

    openings and closings

    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
     starting
    -0.85
    Starting
    -0.76
    aire
    -0.75
     Starting
    -0.74
     startups
    -0.71
     κε
    -0.70
    Scenes
    -0.68
    بح
    -0.68
     logr
    -0.65
     живот
    -0.65
    POSITIVE LOGITS
     Opens
    0.81
     opens
    0.79
    opens
    0.75
     劇場
    0.69
     participante
    0.68
    (@"%@",
    0.68
     Praia
    0.67
    ándote
    0.67
     Grind
    0.66
     administered
    0.66
    Activations Density 0.028%

    No Known Activations