© 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-16K
    7. 1614
    Prev
    Next
    INDEX
    Explanations

    beans, italy, pan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_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
     distaste
    0.25
     evidentemente
    0.24
     tentu
    0.23
     zdravot
    0.23
    مان
    0.23
     estética
    0.22
    ِر
    0.22
     samoz
    0.22
     evidencia
    0.21
     apariencia
    0.21
    POSITIVE LOGITS
    vykor
    0.23
    between
    0.23
     ABSORBED
    0.23
    ycling
    0.23
    ֡
    0.22
     获取
    0.22
     тан
    0.22
     module
    0.22
     Modules
    0.22
     Sequences
    0.22
    Activations Density 0.598%

    No Known Activations