© 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. 28554
    Prev
    Next
    INDEX
    Explanations

    identifying the same

    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
     sometimes
    -1.00
     each
    -0.97
     more
    -0.92
     every
    -0.91
     rarely
    -0.90
     allows
    -0.84
     almost
    -0.83
    biam
    -0.83
     often
    -0.83
    ظهار
    -0.82
    POSITIVE LOGITS
     иден
    1.15
     именно
    1.15
     belong
    1.09
    同じ
    1.05
     recognizable
    1.03
     recognisable
    1.03
    ident
    1.02
    ิลปะ
    1.00
    と同じ
    0.99
     unmistakable
    0.98
    Activations Density 0.094%

    No Known Activations