© 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. 107860
    Prev
    Next
    INDEX
    Explanations

    technical descriptors and code elements

    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
     买
    -0.90
    ↞
    -0.88
    Caracteristici
    -0.86
     ayakkabı
    -0.85
     chargeur
    -0.83
    👟
    -0.83
     bezpečnost
    -0.82
    ressa
    -0.81
     presentaron
    -0.78
    fallout
    -0.77
    POSITIVE LOGITS
     determina
    0.75
     semper
    0.73
     mouseClicked
    0.73
     Attachment
    0.67
    urches
    0.66
     aparte
    0.65
    determin
    0.65
    成品
    0.65
     бе
    0.65
     Poin
    0.65
    Activations Density 0.003%

    No Known Activations