© 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. 47799
    Prev
    Next
    INDEX
    Explanations

    System Preferences

    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
     exhibitions
    -0.79
    phospho
    -0.74
     cursos
    -0.71
    rimir
    -0.71
    lin
    -0.71
    essler
    -0.70
     contextLoads
    -0.69
     sings
    -0.68
    Linear
    -0.68
     JMS
    -0.68
    POSITIVE LOGITS
     навсегда
    0.71
     kubwa
    0.66
     THOUGH
    0.65
    Qualified
    0.65
     permitting
    0.64
    ouvrir
    0.64
     facteurs
    0.62
     Normandy
    0.61
    WIND
    0.60
     Carrying
    0.60
    Activations Density 0.095%

    No Known Activations