© 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. 23809
    Prev
    Next
    INDEX
    Explanations

    role and row coordinates

    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_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
    J
    0.47
    ле
    0.46
    controls
    0.46
    ंडर
    0.45
     small
    0.43
    nia
    0.42
    یکل
    0.42
     controls
    0.42
     controlling
    0.42
    o
    0.41
    POSITIVE LOGITS
     základě
    0.52
     bacilli
    0.49
     Foreground
    0.48
     "")
    0.46
     ଓ
    0.46
     ఏర్ప
    0.46
     ដែល
    0.46
    អេឡិចត្រូនិច
    0.46
     invariant
    0.44
    ")+
    0.44
    Activations Density 0.000%

    No Known Activations