© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42635
    Prev
    Next
    INDEX
    Explanations

    package.json keys

    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
    ন
    1.16
     Tôi
    1.04
     Nh
    0.99
     Той
    0.97
    स
    0.96
    我相信
    0.94
     Perché
    0.93
     Zas
    0.93
    Н
    0.92
    atum
    0.92
    POSITIVE LOGITS
    வ
    1.16
     simili
    1.15
     bisher
    1.13
     comenzar
    1.11
     mayores
    1.09
     obiettivi
    1.09
    '
    1.09
    ’
    1.08
     drei
    1.07
     montar
    1.06
    Activations Density 0.002%

    No Known Activations