© 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. 43643
    Prev
    Next
    INDEX
    Explanations

    completed actions

    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
    曾在
    0.45
     pernah
    0.38
     했던
    0.38
     பாதிக்கப்பட்ட
    0.38
    毘
    0.37
    ្នាក់
    0.37
    Woods
    0.36
    았던
    0.36
    戙
    0.36
    Units
    0.36
    POSITIVE LOGITS
     e
    0.48
     another
    0.46
     finally
    0.46
    を開始
    0.46
     наконец
    0.43
     steadily
    0.43
     finalmente
    0.42
     keen
    0.42
     keenly
    0.41
    barui
    0.41
    Activations Density 0.008%

    No Known Activations