© 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. 30795
    Prev
    Next
    INDEX
    Explanations

    "Where" questions

    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
    ເພື່ອ
    1.32
    ه
    1.32
    েবের
    1.27
    将在
    1.26
    ্লিকেশন
    1.23
    விலான
    1.19
    ST
    1.17
    ی
    1.15
    忑
    1.15
    才知道
    1.13
    POSITIVE LOGITS
    ो
    1.43
    I
    1.38
    ue
    1.31
    er
    1.29
    นั้น
    1.29
    ụ
    1.24
     Isn
    1.20
    ın
    1.20
     canada
    1.20
    Isn
    1.18
    Activations Density 0.019%

    No Known Activations