© 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. 87259
    Prev
    Next
    INDEX
    Explanations

    issue commands, early warning, improved lung

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

    military and technical specifications in documents describing weapons, vehicles, or defense systems.

    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
     violencia
    -0.90
    ッセイ
    -0.84
    🍴
    -0.82
    Ook
    -0.80
    🏟
    -0.80
     ره
    -0.77
    ocios
    -0.77
     NAME
    -0.77
    ḷ
    -0.77
     Luxus
    -0.76
    POSITIVE LOGITS
    windigkeit
    0.97
    keydown
    0.91
    差不
    0.88
     referrerpolicy
    0.88
     reimbursed
    0.86
     artisanal
    0.85
     hoisted
    0.84
     interspersed
    0.82
    italic
    0.82
    ית
    0.81
    Activations Density 0.001%

    No Known Activations