© 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-262K
    7. 2648
    Prev
    Next
    INDEX
    Explanations

    numbers digits

    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
    est
    0.64
     đừng
    0.53
    до
    0.52
    arag
    0.52
    ϲ
    0.51
    ar
    0.51
     Bioinformatics
    0.51
    是非常
    0.50
    ord
    0.49
     Consiglio
    0.49
    POSITIVE LOGITS
    к
    0.70
    ह
    0.62
    ن
    0.59
     demean
    0.55
    ки
    0.55
    ној
    0.55
    <0x80>
    0.53
    )".
    0.53
    具合
    0.53
    hh
    0.52
    Activations Density 0.180%

    No Known Activations