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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5316
    Prev
    Next
    INDEX
    Explanations

    discussions or narratives that connect past experiences to broader themes or concepts, particularly in a nostalgic or reflective context.

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

    past continuous contemplation

    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
    ತ
    0.44
     garnered
    0.40
    Ⲛ
    0.39
     избежать
    0.39
     вмеша
    0.38
     denounced
    0.38
    튼
    0.38
    ዉ
    0.37
     በሚ
    0.37
     derog
    0.37
    POSITIVE LOGITS
     wondering
    0.50
     pondering
    0.45
     reminis
    0.43
     browsing
    0.42
    avage
    0.42
     practicing
    0.41
    諗
    0.41
    mj
    0.40
    อยาก
    0.40
    想着
    0.39
    Activations Density 0.047%

    No Known Activations