© 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-16K
    7. 5892
    Prev
    Next
    INDEX
    Explanations

    promotion of respect and safety

    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_16k_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
    LER
    2.48
    臾
    2.48
     poiché
    2.31
    LOW
    2.19
     причем
    2.16
     Ее
    2.14
    ɱ
    1.91
    NESS
    1.88
    NK
    1.86
     reloc
    1.85
    POSITIVE LOGITS
    ט
    2.45
    स
    2.31
    지
    2.28
    ter
    2.14
    et
    2.13
    س
    2.13
    ch
    2.06
    en
    2.05
    었다
    1.88
    т
    1.88
    Activations Density 0.064%

    No Known Activations