© 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. 22-GEMMASCOPE-RES-131K
    7. 15533
    Prev
    Next
    INDEX
    Explanations

    events and processes

    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
     they
    -1.15
     учиться
    -1.04
     各
    -1.03
    ICIÓN
    -1.01
    স্ত
    -1.00
     inflam
    -0.91
     exis
    -0.91
     bilhões
    -0.91
    maxn
    -0.89
     PHILLIPS
    -0.89
    POSITIVE LOGITS
     conducted
    1.76
     performed
    1.48
     done
    1.41
     に関する
    1.38
     undertaken
    1.32
    ruka
    1.27
     occurring
    1.24
     sessions
    1.22
    ihnachts
    1.21
     során
    1.17
    Activations Density 0.096%

    No Known Activations