© 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. 252905
    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
    морфи
    0.52
     dorso
    0.50
    kých
    0.50
     веществ
    0.49
    羰
    0.49
    ඪ
    0.48
     coval
    0.47
    ocou
    0.47
    秞
    0.47
     ಎರಡು
    0.46
    POSITIVE LOGITS
    0.49
    我知道
    0.45
    ه
    0.45
     Official
    0.44
    What
    0.44
     utama
    0.42
     official
    0.41
    estimating
    0.41
    غ
    0.41
    ط
    0.40
    Activations Density 0.001%

    No Known Activations