© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32742
    Prev
    Next
    INDEX
    Explanations

    adapted and modified

    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
    katan
    -0.84
    getPosition
    -0.83
    両方
    -0.82
     descuentos
    -0.82
    隈
    -0.80
     vagyok
    -0.77
     épaules
    -0.77
    ⍝
    -0.77
    רית
    -0.77
     révolution
    -0.77
    POSITIVE LOGITS
     modified
    4.44
     modifications
    4.00
     adapted
    3.95
     modification
    3.80
    modified
    3.73
     modify
    3.58
     adaptations
    3.56
     adaptation
    3.44
     modific
    3.33
     adapt
    3.25
    Activations Density 0.310%

    No Known Activations