© 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. 36150
    Prev
    Next
    INDEX
    Explanations

    Jay Lerner Lawrence Livermore hawkish

    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
    ্প
    2.25
     independ
    2.03
     infert
    1.94
     concaten
    1.92
     Wonderful
    1.90
     וב
    1.86
    েও
    1.84
    á
    1.82
     astron
    1.81
     hypersurfaces
    1.80
    POSITIVE LOGITS
    ם
    2.50
    ע
    2.22
    el
    2.16
    ive
    2.16
    судар
    1.97
    म
    1.95
    ัน
    1.94
    م
    1.93
    䒑
    1.93
    نا
    1.92
    Activations Density 0.003%

    No Known Activations