© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35764
    Prev
    Next
    INDEX
    Explanations

    doing again

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

    This neuron lights up on the key content words in the user’s narrative description of the cloning story (e.g. “imitation,” “own,” “life,” “redo,” “romance,” “worked”).

    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
    After
    -1.05
     Gattung
    -0.85
    Here
    -0.83
    このように
    -0.83
     heal
    -0.81
     suitable
    -0.81
    Following
    -0.79
     pensieri
    -0.78
     temporary
    -0.77
     demasiado
    -0.77
    POSITIVE LOGITS
    一遍
    1.20
     again
    1.11
    AGAIN
    1.09
    again
    1.05
     znovu
    1.04
    あの
    1.03
     повтор
    1.02
     the
    1.02
     ImportError
    0.99
    bagian
    0.98
    Activations Density 0.059%

    No Known Activations