© 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. 11186
    Prev
    Next
    INDEX
    Explanations

    current state or situation

    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
    ي
    0.79
    י
    0.78
    ও
    0.66
     dinners
    0.64
     electrón
    0.63
    以后
    0.61
    后
    0.61
    ת
    0.60
    도
    0.58
    ্যা
    0.57
    POSITIVE LOGITS
     현재
    1.05
     attuale
    0.96
     huidige
    0.91
     Current
    0.89
     current
    0.88
     वर्तमान
    0.83
    current
    0.82
    目前的
    0.82
     currently
    0.81
    Currently
    0.81
    Activations Density 0.116%

    No Known Activations