© 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. 60211
    Prev
    Next
    INDEX
    Explanations

    proposals and proteins

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

    code syntax elements and programming language patterns, particularly in file headers and license declarations.

    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
     Nieto
    -0.91
     plex
    -0.81
     PUBLIC
    -0.77
    crtc
    -0.74
     Crot
    -0.71
     Riva
    -0.69
     közé
    -0.68
    ιος
    -0.67
     Extension
    -0.67
    ⓝ
    -0.67
    POSITIVE LOGITS
    ͼ
    0.77
     begleiten
    0.68
    られていた
    0.68
     greifen
    0.67
     transferir
    0.66
     sebagai
    0.65
    iones
    0.65
    quakes
    0.64
    لسلة
    0.64
     financieros
    0.64
    Activations Density 0.041%

    No Known Activations