© 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. 252940
    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
     numerador
    0.50
     возле
    0.48
     видим
    0.47
    icional
    0.47
     வித்தியாச
    0.47
     poema
    0.46
     سريع
    0.46
    C
    0.46
     с
    0.45
     следова
    0.45
    POSITIVE LOGITS
     Expedition
    0.45
     cabins
    0.44
     proclamation
    0.42
     exportation
    0.42
    лау
    0.42
     abstracts
    0.42
     Girlfriend
    0.42
     Ecosystem
    0.42
     expedition
    0.41
     condos
    0.41
    Activations Density 0.001%

    No Known Activations