© 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. 20820
    Prev
    Next
    INDEX
    Explanations

    making things easier

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

    The neuron responds to “-ing” forms—that is, gerunds or present‐participle verbs.

    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
    岐
    -1.31
     tdci
    -1.23
    的一些
    -1.22
     mondeo
    -1.22
     ٢
    -1.20
     valentín
    -1.19
     hins
    -1.18
    cial
    -1.18
     €,
    -1.18
     yng
    -1.17
    POSITIVE LOGITS
     —
    1.45
    怖い
    1.30
    ڼ
    1.30
    ourtney
    1.30
    Hauteur
    1.30
     Bedürf
    1.28
    ratislava
    1.27
     desconocido
    1.24
     maravilloso
    1.23
    ToolStripButton
    1.21
    Activations Density 0.146%

    No Known Activations