© 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. 3819
    Prev
    Next
    INDEX
    Explanations

    plays a role / paying attention

    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
    るので
    1.20
    ྒྱ
    1.16
     abrigo
    1.09
    −</
    1.09
     históricos
    1.09
    !\!\
    1.07
    컷
    1.05
    样的
    1.03
    প্প
    1.03
    ຜະລ
    1.02
    POSITIVE LOGITS
    AS
    1.40
    OL
    1.33
    AM
    1.23
    AG
    1.20
    AX
    1.16
    ERICK
    1.13
    EX
    1.11
    ER
    1.10
    IR
    1.08
    OR
    1.06
    Activations Density 0.129%

    No Known Activations