© 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. 34-GEMMASCOPE-RES-131K
    4. 83725
    Prev
    Next
    INDEX
    Explanations

    readily available items

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

    The neuron flags advisory or recommendation phrases—especially imperatives telling the reader to keep or have something.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     entièrement
    -0.90
     Kessel
    -0.88
    adone
    -0.88
    ileen
    -0.87
    estroying
    -0.84
    żs
    -0.84
    ormous
    -0.84
     bestaande
    -0.84
     Nha
    -0.84
     meilleures
    -0.83
    POSITIVE LOGITS
     handy
    2.95
     ready
    2.89
     readily
    2.36
     available
    2.27
     nearby
    2.23
     accessible
    2.20
    ready
    1.91
     sẵn
    1.91
     at
    1.80
     Ready
    1.70
    Activations Density 0.060%

    No Known Activations