© 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. 35463
    Prev
    Next
    INDEX
    Explanations

    Supplemental Security Income, SSDI

    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
    ن
    1.05
    ת
    1.04
    י
    0.98
    й
    0.91
    و
    0.88
    ુ
    0.84
    ي
    0.84
    Gym
    0.83
    奥
    0.83
    에
    0.82
    POSITIVE LOGITS
     perceber
    0.90
    basin
    0.84
     eher
    0.84
     Krueger
    0.82
    bi
    0.80
    idescent
    0.80
    াণী
    0.79
     brine
    0.78
     Gerade
    0.77
    borderwidth
    0.77
    Activations Density 0.000%

    No Known Activations