© 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. 115773
    Prev
    Next
    INDEX
    Explanations

    cytoskeletal scaffolding proteins

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

    protein and molecular structures in scientific papers, particularly those describing interactions between proteins and cellular components.

    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
    zaj
    -0.86
     ATP
    -0.84
     envelopes
    -0.80
    fluss
    -0.79
    Saw
    -0.77
     pine
    -0.76
     Nuclear
    -0.75
     extracellular
    -0.73
    vaj
    -0.71
    ተ
    -0.71
    POSITIVE LOGITS
     scaffolding
    1.18
     adaptor
    1.14
    adapters
    0.97
     scaffold
    0.97
    adaptor
    0.93
    adapt
    0.91
     Scaffold
    0.85
     scaffolds
    0.82
     Adap
    0.82
     Adapter
    0.82
    Activations Density 0.179%

    No Known Activations