© 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. 34-GEMMASCOPE-RES-131K
    7. 91413
    Prev
    Next
    INDEX
    Explanations

    first past

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

    The neuron activates on third-person singular present-tense verb forms (verbs ending in “-s” like walks, drives, gets, sneaks).

    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
    了出去
    -0.91
     последний
    -0.74
    有一天
    -0.71
    lerde
    -0.69
     zegt
    -0.69
    RIT
    -0.69
    最后
    -0.68
    ⋮
    -0.68
     oben
    -0.67
    edere
    -0.67
    POSITIVE LOGITS
     past
    8.63
    past
    6.47
    Past
    6.16
     Past
    5.78
     PAST
    4.97
    過去
    4.63
    PAST
    4.53
     pasado
    4.28
    过去
    4.13
     passado
    3.89
    Activations Density 0.158%

    No Known Activations