© 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. 7524
    Prev
    Next
    INDEX
    Explanations

    HTML/XML tags or elements

    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
    。
    1.22
    乎
    1.20
    ，
    1.17
     autoch
    1.15
     enshr
    1.14
    fordert
    1.14
     amd
    1.12
     youre
    1.12
     amenity
    1.12
     duh
    1.12
    POSITIVE LOGITS
    j
    1.32
    la
    1.31
    ي
    1.21
    ને
    1.20
    İlk
    1.14
    rows
    1.11
    än
    1.11
    ん
    1.11
    lerini
    1.09
     iniziare
    1.09
    Activations Density 0.035%

    No Known Activations