© 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. 252882
    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
    Tom
    0.47
    Tag
    0.46
    Harvey
    0.46
    Toyota
    0.45
    Mumbai
    0.44
    Jur
    0.43
    J
    0.43
    Tak
    0.42
    Jackie
    0.42
     purnama
    0.42
    POSITIVE LOGITS
     mattered
    0.50
     behaving
    0.49
    stwa
    0.49
     self
    0.48
     behaved
    0.48
     привы
    0.47
    islation
    0.47
    婵
    0.46
     authorship
    0.46
     burdened
    0.45
    Activations Density 0.000%

    No Known Activations