© 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. 34-GEMMASCOPE-RES-131K
    7. 115682
    Prev
    Next
    INDEX
    Explanations

    DNA fragmentation and apoptosis

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

    scientific terminology related to cell death and apoptosis processes.

    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_34/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
     walking
    -1.05
    Walking
    -0.85
    walking
    -0.83
     walks
    -0.82
     Walking
    -0.81
     walkers
    -0.77
     walk
    -0.76
     wichtigen
    -0.73
     órdenes
    -0.72
    走路
    -0.72
    POSITIVE LOGITS
     fragmentation
    1.21
     Annex
    1.03
     phosphat
    0.99
     fragmented
    0.97
    Annex
    0.92
    Frag
    0.88
    TUN
    0.86
    fract
    0.85
     fractured
    0.85
    ragment
    0.84
    Activations Density 0.134%

    No Known Activations