© 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. 40-GEMMASCOPE-2-RES-262K
    7. 223409
    Prev
    Next
    INDEX
    Explanations

    loss of memories

    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_40_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
    iov
    0.37
     alimenta
    0.36
    لاميذ
    0.35
    Digest
    0.35
     WEIGHT
    0.35
    ิมพ์
    0.35
    •
    0.35
    iors
    0.34
     फिल्टर
    0.34
     obchod
    0.34
    POSITIVE LOGITS
    ၅
    0.42
    clu
    0.40
    ஸல்
    0.39
    复杂
    0.39
    ümü
    0.39
    处
    0.39
    下去
    0.38
    远
    0.38
     दिश
    0.38
     ವಿ
    0.37
    Activations Density 0.000%

    No Known Activations