© 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. 482
    Prev
    Next
    INDEX
    Explanations

    future outlook and consequences

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

    The neuron detects forward-looking or strategic action language—verbs and connectives that signal planning for future events (e.g. “take…prepare for when,” “position themselves to…,” “will”).

    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
    近年来
    -1.05
     ſou
    -0.99
    PyTuple
    -0.98
     современных
    -0.97
     ***!
    -0.96
     salada
    -0.94
     taal
    -0.94
     современ
    -0.93
     последнее
    -0.92
     Buren
    -0.92
    POSITIVE LOGITS
     will
    1.59
     virus
    1.42
     COVID
    1.42
     recovery
    1.39
     Covid
    1.30
     people
    1.24
     post
    1.19
     coronavirus
    1.19
     new
    1.18
     During
    1.18
    Activations Density 0.006%

    No Known Activations