© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130257
    Prev
    Next
    INDEX
    Explanations

    necrotizing necrosis necrotic

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to tissue death or necrosis, particularly the term "necro" and variations of "necrotic".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    以上です
    -2.98
    ・・・・・・・・
    -2.98
    Ꮞ
    -2.86
    ＝＝＝＝
    -2.84
    Surprisingly
    -2.81
     έχουν
    -2.78
    牁
    -2.75
    情况下
    -2.72
    鸶
    -2.70
    geſ
    -2.67
    POSITIVE LOGITS
    '
    3.81
    "
    3.11
    </h1>
    2.66
    }$
    2.64
     -
    2.55
     )
    2.39
     I
    2.36
     
    2.27
    a
    2.25
     "
    2.23
    Activations Density 0.009%

    No Known Activations