© 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. 116650
    Prev
    Next
    INDEX
    Explanations

    chemical modification or base substitution

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

    programming language code, particularly imports and function 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
    ┊
    -0.83
    köz
    -0.73
     перевод
    -0.73
     маски
    -0.73
    保安
    -0.71
     kritik
    -0.71
     маска
    -0.70
     DNA
    -0.69
     kolei
    -0.69
     cac
    -0.68
    POSITIVE LOGITS
    astrous
    0.80
     base
    0.80
    alker
    0.76
    اعدة
    0.73
     chemical
    0.73
     escaped
    0.73
     įsi
    0.70
    lang
    0.69
     practical
    0.69
     modified
    0.68
    Activations Density 0.056%

    No Known Activations