© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6930
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ine
    1.48
    ut
    1.38
    iske
    1.25
    imantan
    1.25
    ième
    1.23
     inny
    1.23
     बढ़ते
    1.20
    ו
    1.20
    y
    1.20
    ില്‍
    1.18
    POSITIVE LOGITS
     রকমের
    1.24
    .
    1.22
    ຢູ່ໃນ
    1.15
    )、
    1.13
    𝗷
    1.11
     önemlidir
    1.10
     Importantly
    1.09
    )。
    1.07
     differenti
    1.05
     allá
    1.03
    Activations Density 5.045%

    No Known Activations