© 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. 66255
    Prev
    Next
    INDEX
    Explanations

    promise of future

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

    This neuron activates on the word “promise” (and its immediate “of/the” context).

    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
     '
    -2.95
     we
    -2.61
    )
    -2.59
    旆
    -2.36
     представлены
    -2.36
     esche
    -2.34
    ⧠
    -2.33
     mão
    -2.31
    不错的
    -2.31
    ⢅
    -2.30
    POSITIVE LOGITS
    d
    2.39
    м
    2.38
    ная
    2.31
    橼
    2.30
    It
    2.30
    
    2.23
     工場
    2.22
    Académie
    2.19
    will
    2.17
    ной
    2.13
    Activations Density 0.008%

    No Known Activations