© 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. 255053
    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
    𝐞
    0.52
    under
    0.51
    asjon
    0.49
    arne
    0.48
    ionar
    0.48
    ultat
    0.47
    atoren
    0.47
    𝐢
    0.46
    vom
    0.46
    zeum
    0.46
    POSITIVE LOGITS
     reimbursement
    0.50
     crushing
    0.49
     recursive
    0.47
     Magento
    0.46
     prosperous
    0.46
     bureaucracy
    0.46
     USU
    0.46
     anomalous
    0.44
     ambi
    0.44
     reclama
    0.44
    Activations Density 0.002%

    No Known Activations