© 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. 81773
    Prev
    Next
    INDEX
    Explanations

    advance directives, Extended Property, Against Gun, cytology, range, uint, Administratrix, home directory

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

    technical terms and specialized jargon in scientific, medical, or programming contexts.

    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
    ⾥
    -1.55
    ⼝
    -1.51
     umożliwia
    -1.08
    但却
    -0.94
    ⻓
    -0.93
    ᚑ
    -0.91
    —
    -0.91
     và
    -0.88
    /
    -0.84
    ⾳
    -0.83
    POSITIVE LOGITS
    ⾔
    1.13
     „
    1.02
    ⾒
    1.02
    利
    0.93
    ⼿
    0.89
    ⼰
    0.88
    兩
    0.82
    ‟
    0.81
    Добавлено
    0.81
    ಼
    0.78
    Activations Density 17.015%

    No Known Activations