© 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. 67355
    Prev
    Next
    INDEX
    Explanations

    business establishment context

    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
    CCION
    -0.99
    ὺς
    -0.97
     började
    -0.96
    ранее
    -0.96
    —
    -0.94
     preferido
    -0.93
     néz
    -0.90
     ImportError
    -0.90
     alltså
    -0.90
     gyrus
    -0.90
    POSITIVE LOGITS
    received
    1.09
    probably
    1.08
     pesso
    1.03
     setup
    1.02
     simbo
    1.02
     solidari
    1.02
     vernac
    1.02
     coelho
    1.00
     sereia
    1.00
    (!__
    1.00
    Activations Density 0.029%

    No Known Activations