© 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. 22-GEMMASCOPE-RES-131K
    4. 36527
    Prev
    Next
    INDEX
    Explanations

    in vivo / in situ / on-site / real time

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

    The neuron detects phrases related to real-world environments or settings, particularly scientific terms like "in vivo", "on-scene", "in situ", and "real-time".

    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
    Village
    -0.92
    ilangkan
    -0.90
    Produto
    -0.90
    pēc
    -0.90
    น่า
    -0.90
    leté
    -0.89
    ");
    
    -0.88
    囑
    -0.86
    );
    
    -0.84
     området
    -0.84
    POSITIVE LOGITS
    Unlike
    0.93
    フレッシュ
    0.90
    かもしれない
    0.89
    他想
    0.89
     unlike
    0.89
    ereo
    0.88
    ⦑
    0.85
    utat
    0.83
    派的
    0.83
     absurdo
    0.83
    Activations Density 0.125%

    No Known Activations