© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 32131
    Prev
    Next
    INDEX
    Explanations

    python config or typing

    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_262k_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
    .
    0.86
    :
    0.74
    )
    0.69
    。
    0.66
    ْل
    0.64
    "
    0.64
    {
    0.64
    0.64
    ]
    0.62
     compared
    0.62
    POSITIVE LOGITS
     S
    0.70
    ampton
    0.69
    ទទួលបាន
    0.67
    tand
    0.66
    odni
    0.65
    et
    0.64
     اسئله
    0.63
     comorbidities
    0.63
     resonances
    0.62
    ொள்ள
    0.61
    Activations Density 0.024%

    No Known Activations