© 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. 256890
    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
    მე
    0.54
    و
    0.51
     Weierstrass
    0.48
    य्
    0.47
    WithFieldContext
    0.44
    濵
    0.44
    痙
    0.44
    拟
    0.43
    约束
    0.43
    Questa
    0.43
    POSITIVE LOGITS
    0.48
     regained
    0.47
     reserv
    0.43
     susp
    0.43
     installation
    0.42
     heard
    0.42
     Built
    0.42
     противо
    0.42
     Opportunity
    0.42
    chal
    0.41
    Activations Density 0.000%

    No Known Activations