© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39801
    Prev
    Next
    INDEX
    Explanations

    RE and FW email subjects

    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
     suí
    -1.17
    舠
    -1.16
     ensino
    -1.13
     jardim
    -1.02
     вещи
    -1.01
     querem
    -1.01
     conteúdo
    -1.00
    全て
    -0.99
     confortável
    -0.98
     великий
    -0.97
    POSITIVE LOGITS
     begre
    1.18
     herstellen
    1.07
     konkrete
    1.05
     belast
    1.05
     Daar
    1.05
    sproble
    1.04
     ajang
    1.02
     Жи
    1.01
     sommer
    1.00
     klasse
    1.00
    Activations Density 0.009%

    No Known Activations