© 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. 344
    Prev
    Next
    INDEX
    Explanations

    approaches for creating knowledge bases.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    actions and purposes

    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
    。
    0.21
     чтобы
    0.17
    ().
    0.16
     eliminating
    0.16
     setzt
    0.16
     setzen
    0.16
    .
    0.16
     removing
    0.16
     เพื่อ
    0.16
     删除
    0.15
    POSITIVE LOGITS
    ppled
    0.16
     consider
    0.14
     have
    0.14
     beheld
    0.13
     a
    0.13
     look
    0.13
    στηκε
    0.13
     conceptual
    0.13
     haunt
    0.13
     wreak
    0.13
    Activations Density 0.650%

    No Known Activations