© 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. 13869
    Prev
    Next
    INDEX
    Explanations

    making or understanding something

    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
    ur
    2.02
    ir
    1.98
    ies
    1.95
    am
    1.86
    í
    1.85
    কিন্ত
    1.77
    w
    1.76
    im
    1.74
     priors
    1.73
    h
    1.71
    POSITIVE LOGITS
    νου
    1.80
    ా
    1.70
    dır
    1.61
    ج
    1.59
    ът
    1.52
    скоре
    1.51
    с
    1.50
    彡
    1.49
    ্স
    1.48
    пра
    1.44
    Activations Density 0.011%

    No Known Activations