© 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. 28253
    Prev
    Next
    INDEX
    Explanations

    current status or recent updates

    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
     landet
    -0.98
     раза
    -0.97
    selection
    -0.90
    ографи
    -0.90
     incred
    -0.87
     gevonden
    -0.86
     Pacific
    -0.86
    expected
    -0.86
     specification
    -0.85
    nexpected
    -0.85
    POSITIVE LOGITS
     status
    1.24
     recent
    1.16
     current
    1.09
    Recently
    1.02
    现状
    0.98
     недавно
    0.94
     recently
    0.93
     recientemente
    0.91
     statuses
    0.91
    зумі
    0.90
    Activations Density 0.009%

    No Known Activations