© 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. 9069
    Prev
    Next
    INDEX
    Explanations

    identify the specifics

    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
    i
    2.27
    u
    2.08
    ه
    1.91
    s
    1.88
    w
    1.83
    t
    1.75
    y
    1.70
    yl
    1.59
    c
    1.58
    a
    1.53
    POSITIVE LOGITS
    اس
    1.59
    РЕ
    1.50
    𝒊
    1.41
    𝐼
    1.41
    𝑰
    1.41
    Р
    1.40
    о
    1.39
    𝑳
    1.34
    Ο
    1.29
    𝙎
    1.28
    Activations Density 0.001%

    No Known Activations