© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 250853
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    0.44
    ritus
    0.43
    ποίη
    0.43
    rooted
    0.42
     elders
    0.41
    calling
    0.41
    쾰
    0.41
    梱包
    0.40
     ዓይነ
    0.40
     patriarchal
    0.40
    POSITIVE LOGITS
     Silk
    0.44
     উৎক
    0.40
     Sog
    0.39
    Blo
    0.38
     সুল
    0.38
     sculptor
    0.38
     POS
    0.37
     Rayleigh
    0.37
    棉
    0.36
    anga
    0.36
    Activations Density 0.041%

    No Known Activations