© 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. 106966
    Prev
    Next
    INDEX
    Explanations

    N- and C-termini

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

    protein structures with amino-terminal or carboxy-terminal domains.

    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
     upper
    -0.88
     oberen
    -0.81
    говор
    -0.81
    upper
    -0.81
    chats
    -0.79
    ября
    -0.76
    cillor
    -0.75
     miten
    -0.74
     solidaridad
    -0.73
    льник
    -0.72
    POSITIVE LOGITS
     N
    2.13
     terminal
    2.11
     C
    2.03
    terminal
    1.80
     terminus
    1.67
     terminals
    1.62
     Terminal
    1.57
    Terminal
    1.51
    N
    1.45
    termin
    1.41
    Activations Density 0.130%

    No Known Activations