© 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. 40821
    Prev
    Next
    INDEX
    Explanations

    social studies education

    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
    est
    1.36
    溲
    1.30
    ﭑ
    1.16
    であり
    1.16
     I
    1.15
    𝒶
    1.13
     Hàm
    1.12
     Ś
    1.09
     І
    1.09
     Ι
    1.09
    POSITIVE LOGITS
    lere
    1.54
    ς
    1.45
    lük
    1.40
    '};
    1.39
    s
    1.38
    dür
    1.36
    lardan
    1.34
    vät
    1.34
    yiz
    1.34
    lend
    1.33
    Activations Density 0.000%

    No Known Activations