© 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. 4386
    Prev
    Next
    INDEX
    Explanations

    listening, healthy society, relationships

    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
    bogen
    1.09
    ல்லிய
    0.96
    eigen
    0.88
    욜
    0.88
     новогод
    0.86
    gten
    0.86
     změ
    0.85
     bleu
    0.84
    ственным
    0.84
    emetery
    0.82
    POSITIVE LOGITS
    কে
    0.78
    বর্তী
    0.74
    াচার
    0.74
    के
    0.73
     PR
    0.73
    リーズ
    0.73
     Avocado
    0.73
    的工作
    0.73
    ↵
    0.72
    рін
    0.72
    Activations Density 0.164%

    No Known Activations