© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68139
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_22/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
     in
    -1.59
     by
    -1.35
     with
    -1.25
     all
    -1.15
     on
    -1.12
    ओं
    -1.10
    
    -1.07
    Beskrivning
    -1.05
     ū
    -1.04
    しと
    -1.04
    POSITIVE LOGITS
    diğiniz
    1.16
     rostros
    1.09
     consiguiente
    1.08
     なお
    1.07
     speziell
    1.06
    ר
    1.05
    ри
    1.02
     conformidad
    1.02
    伊朗
    1.00
     '--
    0.98
    Activations Density 0.005%

    No Known Activations