© 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. 57138
    Prev
    Next
    INDEX
    Explanations

    coding operations and data structures

    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
     muzy
    -0.93
     who
    -0.91
     durch
    -0.89
     Desenvolvimento
    -0.88
     widok
    -0.87
    unyi
    -0.86
     enth
    -0.86
     umie
    -0.84
    vende
    -0.84
     zespołu
    -0.84
    POSITIVE LOGITS
     lina
    0.89
    chè
    0.89
     pablo
    0.88
     Alhambra
    0.88
     otak
    0.86
    馴
    0.85
     strix
    0.85
    íso
    0.85
     yong
    0.84
     samsung
    0.84
    Activations Density 0.062%

    No Known Activations