© 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. 34-GEMMASCOPE-RES-131K
    7. 64123
    Prev
    Next
    INDEX
    Explanations

    measurement and experimental setup

    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_34/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
     Utilizing
    -1.32
     Jardín
    -1.25
     démarrage
    -1.19
     Compañ
    -1.18
     Señora
    -1.18
     Meksi
    -1.16
     seperate
    -1.13
     Zoltán
    -1.13
     réglage
    -1.12
     geene
    -1.11
    POSITIVE LOGITS
     punctual
    1.38
    ´
    1.26
     pondered
    1.23
     codif
    1.13
     escenario
    1.11
     correspondent
    1.11
     promissory
    1.09
     belonging
    1.05
     detriment
    1.02
     supposes
    1.02
    Activations Density 0.747%

    No Known Activations