© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116928
    Prev
    Next
    INDEX
    Explanations

    genomic, effect of

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

    programming language syntax elements like type declarations, class derivations, and compiler attributes.

    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
    ейс
    -0.88
     Référence
    -0.85
    ⵏ
    -0.82
     Catalog
    -0.79
    Catalog
    -0.79
     mère
    -0.78
     Holly
    -0.77
     Seinfeld
    -0.74
     censo
    -0.73
    bibitem
    -0.73
    POSITIVE LOGITS
    Eq
    1.02
     Debug
    1.00
     Clone
    0.97
    Debug
    0.96
     debug
    0.96
    rovnik
    0.94
     equality
    0.93
    equality
    0.91
     Eq
    0.91
     copy
    0.90
    Activations Density 0.004%

    No Known Activations