© 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-16K
    7. 967
    Prev
    Next
    INDEX
    Explanations

    deep magenta, large

    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
    an
    1.55
    aient
    1.23
    en
    1.20
     şekilde
    1.17
    ال
    1.16
    р
    1.16
    LL
    1.14
    AY
    1.14
    います
    1.13
    いますが
    1.13
    POSITIVE LOGITS
    ों
    1.17
    я
    0.99
    𝚁
    0.96
    s
    0.95
    ς
    0.95
     rato
    0.94
    ປະ
    0.91
    互联网档案馆
    0.90
    으로서
    0.89
     (>
    0.88
    Activations Density 0.332%

    No Known Activations