© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10517
    Prev
    Next
    INDEX
    Explanations

    negotiate, negotiations, ceasefire

    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_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
    м
    2.61
    م
    2.48
    m
    1.80
    t
    1.80
    으로써
    1.74
    nd
    1.61
    ंनी
    1.59
    (\
    1.55
    ['
    1.48
    la
    1.48
    POSITIVE LOGITS
    ﻪ
    1.91
     tenths
    1.82
     esforços
    1.79
     Nella
    1.78
     Esto
    1.76
    𝙇
    1.76
     situés
    1.73
    ரஜன்
    1.73
     mercados
    1.72
     felices
    1.71
    Activations Density 0.003%

    No Known Activations