© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3421
    Prev
    Next
    INDEX
    Explanations

    preserving or maintaining things/people

    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
    ام
    1.21
     distracted
    1.14
    ্যু
    1.13
    ット
    1.05
    既然
    1.05
    وم
    1.03
    أ
    1.03
    om
    1.02
    症
    1.02
    ተ
    1.02
    POSITIVE LOGITS
    รักษา
    1.33
     giữ
    1.27
    да
    1.27
     Spare
    1.25
     Sails
    1.24
     inclui
    1.23
     komme
    1.21
     રાખ
    1.20
     Preservation
    1.20
     Saves
    1.16
    Activations Density 0.262%

    No Known Activations