© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 13820
    Prev
    Next
    INDEX
    Explanations

    los angeles

    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
    mäßig
    1.91
     kuin
    1.88
     compreensão
    1.82
     étab
    1.80
     außer
    1.73
     arrêter
    1.70
    mäßige
    1.68
    ઈ
    1.63
     كه
    1.62
     článku
    1.55
    POSITIVE LOGITS
    ла
    2.27
    り
    2.11
    i
    2.02
    ما
    1.86
    יות
    1.80
    ে
    1.71
    rence
    1.70
    iation
    1.63
    piel
    1.63
    ü
    1.57
    Activations Density 0.047%

    No Known Activations