© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 15032
    Prev
    Next
    INDEX
    Explanations

    fence/fencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    та
    1.67
    і
    1.60
    ן
    1.52
    на
    1.45
     مؤرشف
    1.44
    𝐩
    1.36
    іо
    1.35
    у
    1.30
     oldu
    1.30
    MDA
    1.30
    POSITIVE LOGITS
    or
    1.92
    ao
    1.74
    ﻴ
    1.67
    ческие
    1.64
     fences
    1.64
    ੀ
    1.64
    не
    1.63
    특별시
    1.60
    iert
    1.59
    j
    1.56
    Activations Density 0.008%

    No Known Activations