© 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. 259212
    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
    .')
    0.51
    ’
    0.47
    acan
    0.46
    λο
    0.46
    yta
    0.46
     করেছিলেন
    0.45
    rea
    0.45
     (
    0.44
    anta
    0.44
    ார்
    0.44
    POSITIVE LOGITS
     campaigners
    0.59
     внутренних
    0.54
     ساخت
    0.52
    キャンペーン
    0.52
     campaigning
    0.50
     campanha
    0.50
     стрелец
    0.48
     ინტერ
    0.48
     الخمسه
    0.47
     построе
    0.47
    Activations Density 0.002%

    No Known Activations