© 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. 10923
    Prev
    Next
    INDEX
    Explanations

    listing recommendations and descriptions

    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
    для
    -1.01
    время
    -0.98
     gyhoeddwyd
    -0.97
     konnten
    -0.96
     همان
    -0.96
    '}),
    -0.93
    כא
    -0.93
    GENERIC
    -0.93
    ẨM
    -0.92
    uração
    -0.92
    POSITIVE LOGITS
     this
    1.89
     also
    1.26
     these
    1.15
     such
    1.13
     inclusion
    1.03
    همچنین
    1.02
    そして
    1.02
     pimenta
    1.00
     také
    0.99
     additionally
    0.98
    Activations Density 0.076%

    No Known Activations