© 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. 8849
    Prev
    Next
    INDEX
    Explanations

    best, most, overall, luxurious, acting

    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
    t
    1.09
    h
    0.97
    f
    0.84
    d
    0.84
    le
    0.84
     "
    0.82
    р
    0.81
    _
    0.81
     "/
    0.79
    _",
    0.75
    POSITIVE LOGITS
     décerné
    0.90
    gitian
    0.82
     parmi
    0.80
     जबकि
    0.80
    而在
    0.79
    whereas
    0.78
    在该
    0.77
     tandis
    0.75
     দাঁড়
    0.75
     menunjukkan
    0.74
    Activations Density 0.175%

    No Known Activations