© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1615
    Prev
    Next
    INDEX
    Explanations

    famous people, characters, or concepts

    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_31_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
     Yemen
    0.64
     pesantren
    0.64
     bijvoorbeeld
    0.63
     tesam
    0.62
     `--
    0.62
     ranging
    0.61
     `@
    0.60
     Korean
    0.59
     Cisco
    0.59
     Oman
    0.59
    POSITIVE LOGITS
     berühm
    0.72
    有名な
    0.67
    绚
    0.67
    genius
    0.64
    ஸ்ட
    0.59
    čnog
    0.58
     fyra
    0.58
    娴
    0.58
    జ్ఞ
    0.57
     ünlü
    0.57
    Activations Density 1.033%

    No Known Activations