© 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. 12927
    Prev
    Next
    INDEX
    Explanations

    proper names and technical terms

    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
    </h1>
    -1.03
     /
    -0.90
     zufolge
    -0.88
     Will
    -0.87
    sta
    -0.86
    </h5>
    -0.86
     „
    -0.85
     using
    -0.85
    尤其是
    -0.84
    ra
    -0.84
    POSITIVE LOGITS
    Penjelasan
    1.07
     weft
    1.01
     emprend
    0.96
     ストア
    0.95
    ίο
    0.92
     llenar
    0.92
    recrow
    0.92
     berbagai
    0.91
     Sopho
    0.90
     エリア
    0.89
    Activations Density 0.409%

    No Known Activations