© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90558
    Prev
    Next
    INDEX
    Explanations

    exceptions and exclusions

    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
     distintos
    -1.08
     appropriate
    -0.99
     diversas
    -0.94
     unsuspecting
    -0.94
     jopa
    -0.93
     nawet
    -0.92
     khususnya
    -0.92
     навіть
    -0.91
     relevant
    -0.90
     even
    -0.88
    POSITIVE LOGITS
     anything
    1.19
    excluded
    1.11
     already
    1.04
     unless
    1.00
     excluded
    1.00
    hwnd
    0.98
    already
    0.94
    เกิน
    0.94
     any
    0.93
     bereits
    0.91
    Activations Density 0.068%

    No Known Activations