© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5901
    Prev
    Next
    INDEX
    Explanations

    throughout the

    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
    ewną
    0.55
     இன்னொரு
    0.53
     unul
    0.52
    કારી
    0.48
     данном
    0.48
     ၂
    0.47
     reciente
    0.47
     pourrait
    0.47
    ।"
    0.46
     ਉਨ੍ਹਾਂ
    0.46
    POSITIVE LOGITS
     throughout
    0.99
    Throughout
    0.96
     Throughout
    0.84
     across
    0.66
    0
    0.66
     suốt
    0.65
     boyunca
    0.64
    整个
    0.62
    ين
    0.61
    整個
    0.60
    Activations Density 0.083%

    No Known Activations