© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 254178
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addNew
    0.52
    ondi
    0.52
    ilibre
    0.48
    addElement
    0.48
     saludables
    0.48
     eneste
    0.46
    麾
    0.45
     aplatis
    0.45
     comparten
    0.44
    uiden
    0.44
    POSITIVE LOGITS
    р
    0.53
    D
    0.51
    сло
    0.51
    ด
    0.49
    ת
    0.48
    Gust
    0.48
    сер
    0.47
    фек
    0.47
    ר
    0.47
     drama
    0.46
    Activations Density 0.001%

    No Known Activations