© 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. 12964
    Prev
    Next
    INDEX
    Explanations

    elements and combinations

    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
     похоже
    2.42
     инструк
    2.14
    傥
    1.98
    อัต
    1.98
     источ
    1.97
     absol
    1.94
    tube
    1.91
    ture
    1.88
     основ
    1.88
    호를
    1.88
    POSITIVE LOGITS
    ים
    3.14
    ні
    2.52
    та
    2.22
    sı
    1.99
    ae
    1.98
    im
    1.93
    і
    1.91
    র
    1.91
    ר
    1.89
    ет
    1.88
    Activations Density 0.113%

    No Known Activations