© 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. 252548
    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
     vijj
    0.50
     janela
    0.48
     zombie
    0.46
     potion
    0.46
     कप
    0.45
     soma
    0.45
     hwnd
    0.45
     (;
    0.44
     sun
    0.44
    വശ
    0.44
    POSITIVE LOGITS
    Ly
    0.47
     optim
    0.46
    Seamless
    0.46
     dehydrogen
    0.46
    ه
    0.45
    Ned
    0.45
    Et
    0.44
    GAL
    0.44
    Eff
    0.44
    Fluid
    0.44
    Activations Density 0.000%

    No Known Activations