© 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. 35479
    Prev
    Next
    INDEX
    Explanations

    of behavior, research, role, book, product, content

    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
     puertos
    1.16
     precisa
    1.13
    முகச்
    1.13
     aulas
    1.12
    Sumber
    1.11
     verhindern
    1.09
    և
    1.09
     preferencias
    1.07
     parecen
    1.07
    puede
    1.07
    POSITIVE LOGITS
    োর
    1.24
     commemorating
    1.08
    ু
    1.05
    어져
    1.04
     commenting
    1.00
     extravagance
    0.98
    лығы
    0.98
    ת
    0.96
    𝙞
    0.96
     edt
    0.96
    Activations Density 0.003%

    No Known Activations