© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25463
    Prev
    Next
    INDEX
    Explanations

    arrival or return

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

    The neuron fires on words that indicate someone or something arriving, appearing, or moving into a scene.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ↵
    -1.08
    上的
    -1.05
    </em>
    -1.03
    ほら
    -1.01
     отправи
    -1.01
    all
    -0.99
    ila
    -0.99
    REMOV
    -0.99
    このように
    -0.98
    2
    -0.97
    POSITIVE LOGITS
     to
    1.20
     and
    1.11
     عر
    1.02
     rồi
    0.99
    cheque
    0.98
    приятия
    0.97
    ılıyor
    0.96
    vía
    0.93
    棹
    0.93
     papild
    0.92
    Activations Density 0.058%

    No Known Activations