© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10900
    Prev
    Next
    INDEX
    Explanations

    avoiding repetition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
     TIC
    0.44
    ⁱ
    0.43
     elastomer
    0.42
    icone
    0.42
    otene
    0.42
    ສ່ວນ
    0.41
    qualiter
    0.41
     ফেলেছে
    0.40
     হয়েছেন
    0.40
     Average
    0.39
    POSITIVE LOGITS
     języ
    0.49
    重要
    0.44
    बरी
    0.44
    xcsche
    0.42
    じ
    0.42
    表示
    0.41
    Cheese
    0.41
     pontos
    0.41
     fromage
    0.41
    ة
    0.41
    Activations Density 0.006%

    No Known Activations