© 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. 11466
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ف
    2.48
    ח
    2.39
    т
    1.92
     Mesmo
    1.86
    ください
    1.80
    نا
    1.79
    uc
    1.77
     було
    1.68
    ع
    1.66
    crazy
    1.60
    POSITIVE LOGITS
    ل
    1.88
    ა
    1.61
     allegiance
    1.59
     warahmatullahi
    1.55
     Xét
    1.55
    ти
    1.55
     defamation
    1.51
     habitation
    1.51
    िक
    1.49
    ла
    1.48
    Activations Density 0.004%

    No Known Activations