© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33728
    Prev
    Next
    INDEX
    Explanations

    engines and combustion components

    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
    Questão
    -1.29
    甚至
    -1.23
     mnoho
    -1.22
     treino
    -1.19
     even
    -1.19
     Bewußt
    -1.16
     molti
    -1.14
    立刻
    -1.13
     çünkü
    -1.13
     koszt
    -1.12
    POSITIVE LOGITS
     during
    1.48
    🥴
    1.39
     évé
    1.37
     Octobre
    1.34
     aluminio
    1.33
     MARIE
    1.33
    ☺☺
    1.30
    😫
    1.30
     lørdag
    1.30
     בשנת
    1.29
    Activations Density 0.005%

    No Known Activations