© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20950
    Prev
    Next
    INDEX
    Explanations

    looking forward

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

    The neuron detects words and phrases that indicate forward-looking or future orientation (e.g. “ahead,” “future,” “looking ahead,” “beyond”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ほとんど
    -1.72
    ൅
    -1.63
    nessy
    -1.62
    椤
    -1.59
     洗面
    -1.58
     geprü
    -1.57
    edade
    -1.51
     ""],
    -1.49
     ANCHE
    -1.45
    　　「
    -1.44
    POSITIVE LOGITS
    an
    2.00
     '
    1.88
     ,
    1.78
    ’
    1.74
    '
    1.63
    ，
    1.60
     (?
    1.59
     fondly
    1.59
    c
    1.53
    “
    1.52
    Activations Density 0.022%

    No Known Activations