© 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. 86585
    Prev
    Next
    INDEX
    Explanations

    so far so good

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

    The neuron fires on single‐word verbs or verb forms (e.g. past tense or base‐form action/state words).

    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
     to
    -3.72
     of
    -1.81
    -
    -1.70
     if
    -1.67
     that
    -1.48
    几分
    -1.48
     –
    -1.45
     anybody
    -1.41
    }
    -1.41
     .
    -1.36
    POSITIVE LOGITS
     bolí
    1.61
    どうやって
    1.44
     bosques
    1.42
    푆
    1.38
    僰
    1.38
    ⎚
    1.38
    慊
    1.36
     povo
    1.35
     traductions
    1.34
    бая
    1.34
    Activations Density 0.112%

    No Known Activations