© 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. 11234
    Prev
    Next
    INDEX
    Explanations

    abolition and slavery

    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
     സര്‍ക്കാര്‍
    1.38
    多い
    1.34
    IOUS
    1.32
    ỏe
    1.32
    USTOM
    1.30
     různ
    1.29
    ྪ
    1.28
    ẳng
    1.25
    łki
    1.25
     выходит
    1.23
    POSITIVE LOGITS
    1.36
    ו
    1.34
    もっと
    1.29
    e
    1.25
    -
    1.25
    epe
    1.23
    ти
    1.20
     NIV
    1.16
    ווי
    1.16
    ما
    1.15
    Activations Density 0.009%

    No Known Activations