© 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. 10996
    Prev
    Next
    INDEX
    Explanations

    experimental results and observations

    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
    ></
    -1.10
    ictwo
    -1.07
    請問
    -1.05
    𐍆
    -1.05
    PasswordEncoder
    -1.04
    FilterChain
    -1.04
    닙
    -1.04
    ERSHIP
    -1.02
     computation
    -1.02
     utiliser
    -0.98
    POSITIVE LOGITS
    zmm
    1.15
     data
    1.11
    悯
    1.09
    experimental
    1.09
    reality
    1.05
     tertinggi
    1.05
    EXPERIMENTAL
    1.04
     Geduld
    1.02
     hardware
    1.02
    unexpected
    1.00
    Activations Density 0.083%

    No Known Activations