© 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. 1787
    Prev
    Next
    INDEX
    Explanations

    real name, truly random

    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
    s
    2.19
    یم
    1.91
     Бе
    1.84
    Бе
    1.84
    ه
    1.73
    ים
    1.72
    ्स
    1.71
    )،
    1.66
    ς
    1.65
    ல்
    1.64
    POSITIVE LOGITS
    IST
    1.61
    р
    1.61
    诰
    1.59
    benar
    1.59
    teste
    1.55
    politik
    1.55
    blooded
    1.55
    จริง
    1.53
    痹
    1.52
    nosed
    1.51
    Activations Density 0.710%

    No Known Activations