© 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-262K
    7. 7867
    Prev
    Next
    INDEX
    Explanations

    multilingualism

    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_262k_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
    a
    1.25
    versive
    1.21
    ق
    1.10
    عيب
    1.05
    erc
    1.05
    ktion
    1.05
    क़
    1.03
    comer
    1.03
    ering
    1.02
    precio
    1.02
    POSITIVE LOGITS
     préférable
    1.30
    ⿲
    1.19
     într
    1.16
    ЛИ
    1.16
     ανθρώ
    1.16
    데
    1.16
    諰
    1.16
    CH
    1.13
     kwamba
    1.11
    دە
    1.10
    Activations Density 0.548%

    No Known Activations