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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92544
    Prev
    Next
    INDEX
    Explanations

    genetic mutations and variants

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

    The neuron identifies genetic mutations and sequences, particularly focusing on amino acid sequences, variants, and domains in scientific literature.

    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
     erreicht
    -0.86
     dimentic
    -0.85
    同步
    -0.85
     Untuk
    -0.84
     svilupp
    -0.82
    meliharaan
    -0.82
     lewat
    -0.81
     various
    -0.81
    Pixmap
    -0.81
    MT
    -0.81
    POSITIVE LOGITS
     encoding
    1.37
     located
    1.30
    located
    1.28
     responsible
    1.18
     encoded
    1.09
     encode
    1.09
     that
    1.05
    responsible
    1.05
    encoded
    1.01
     encodes
    0.99
    Activations Density 0.266%

    No Known Activations