© 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. 22-GEMMASCOPE-RES-131K
    7. 39826
    Prev
    Next
    INDEX
    Explanations

    field, gene, dosage, conversion

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

    property and attribute references in code, particularly when accessing fields, keys, or values in programming languages.

    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_22/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
     žena
    -1.14
     explicado
    -1.10
     periódico
    -1.08
    רכז
    -1.04
     nowej
    -1.03
     verdaderos
    -1.03
    deserved
    -1.02
    ࿊
    -1.02
    シェル
    -0.95
    それほど
    -0.95
    POSITIVE LOGITS
     but
    0.92
    比
    0.91
     比
    0.90
    Same
    0.90
    same
    0.89
     same
    0.89
    macro
    0.88
    🤬
    0.87
    original
    0.87
     techniques
    0.86
    Activations Density 0.001%

    No Known Activations